Huggy

Huggy.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce5d67064fa69662ae990a539c1c364070d3848899123dc6f0a55596c989debf
+size 2274020

Huggy/Huggy-1199966.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5256a2d173a9b713530ad6f11f482f9050392d68f3fe3f159c3ea740c761bb55
+size 2274020

Huggy/Huggy-1199966.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0b361b04443cd29d76060bc9f413bec31740ac902e3e486584fcc5900558c65
+size 13509473

Huggy/Huggy-1399994.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f44bd2329e8328b8974f28644ea7254fd513100a3ba3f4107b94143ef0d9f15e
+size 2274020

Huggy/Huggy-1399994.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30920db1450d05faf11b4ca0438eaf5ee20992798c185f37996f5e10a98d6262
+size 13509473

Huggy/Huggy-1599572.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fad9aa0a6bb29d8462deb64788c28c3a8e60537634d350c2145fe63f5c34103c
+size 2274020

Huggy/Huggy-1599572.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b445b9b5d68f2b162a0d491d96e66657cc7706bb8a6cf019037dac4d6beebd
+size 13509473

Huggy/Huggy-1799988.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d258e3a60ba232451aa7b26e1025c8ac9a021ab8a08ce4d80abc5d24752c35c
+size 2274020

Huggy/Huggy-1799988.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82dc92398b465743e8ef1980a7d5d5ad7091ef75fd389108ce618fd99e91348b
+size 13509473

Huggy/Huggy-199890.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2555635e2225c90b27f4af99954350eee4ec9f1e6e916e67c2f43c71b26430c4
+size 2274020

Huggy/Huggy-199890.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:239176e4c5efcb95f504a943d6a93329c50831ca0dec82bc91c34a8a2360d431
+size 13509388

Huggy/Huggy-1999958.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dd11dfb0fa8f97af65946a9d9dd8a3afee2980c1747eea213a7807bb9c46b33
+size 2274020

Huggy/Huggy-1999958.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45e7604daa87f3edc7686cf4ed66f67522d9df820841d905bfc44a03118f4b37
+size 13509473

Huggy/Huggy-2000059.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce5d67064fa69662ae990a539c1c364070d3848899123dc6f0a55596c989debf
+size 2274020

Huggy/Huggy-2000059.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf8c3397ed7e8b8ab0f84dafa20cf8de4656543d22726211edca125a608c0526
+size 13509473

Huggy/Huggy-399944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a6fe4f372a16f3d4c26598d4e149aabdcb4208e46b4f00b6892159aa3c652d0
+size 2274020

Huggy/Huggy-399944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aa84e5c79f879cfa3be3cfadbe5fd630b9a8d663cf7fc22bee8cf661e9009a5
+size 13509388

Huggy/Huggy-599900.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cd74f248ac172f55cfcc508f35b46b3bcbe2e2bb883571b98f7f3cd8022dc3a
+size 2274020

Huggy/Huggy-599900.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:774f8185aa4c2e962ac1fbb1c13ddce773107697d7b7813a61844b13227c2e85
+size 13509388

Huggy/Huggy-799968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e201efbc2bf5aa13bde4e2effd0950f58ac29b0c2626ed16a45dcebddc735004
+size 2274020

Huggy/Huggy-799968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ebae8d2ad67e85672a3925268f21c934be454c2c6ef380f1028f4cb5e2d834c
+size 13509388

Huggy/Huggy-999884.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:866d85e9eec6a42a24ccf2bc56feb2b41c590ce88c25cdcc1bee105e94dd21a7
+size 2274020

Huggy/Huggy-999884.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab6f7b848b24fc75cbe21c522d14675a9d1153ae2236c5e016f4b0f473229003
+size 13509388

Huggy/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22ad14b9398be3ced5391aa5800716edb834d20794d873c1bc5e4a556d30cd3a
+size 13509218

Huggy/events.out.tfevents.1728381354.2eb9519bc3d8.3942.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:778a8708ff553041ea85e61e15ff260385e95aadec6d48d233f66901b0400fee
+size 341457

README.md

@@ -1,37 +1,35 @@
 ---
-library_name: stable-baselines3
+library_name: ml-agents
 tags:
-- LunarLander-v2
+- Huggy
 - deep-reinforcement-learning
 - reinforcement-learning
-- stable-baselines3
-model-index:
-- name: PPO
-  results:
-  - task:
-      type: reinforcement-learning
-      name: reinforcement-learning
-    dataset:
-      name: LunarLander-v2
-      type: LunarLander-v2
-    metrics:
-    - type: mean_reward
-      value: 254.29 +/- 24.97
-      name: mean_reward
-      verified: false
+- ML-Agents-Huggy
 ---
 
-# **PPO** Agent playing **LunarLander-v2**
-This is a trained model of a **PPO** agent playing **LunarLander-v2**
-using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+  # **ppo** Agent playing **Huggy**
+  This is a trained model of a **ppo** agent playing **Huggy**
+  using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
 
-## Usage (with Stable-baselines3)
-TODO: Add your code
+  ## Usage (with ML-Agents)
+  The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
 
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+  - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
+  browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
+  - A *longer tutorial* to understand how works ML-Agents:
+  https://huggingface.co/learn/deep-rl-course/unit5/introduction
 
-```python
-from stable_baselines3 import ...
-from huggingface_sb3 import load_from_hub
+  ### Resume the training
+  ```bash
+  mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
+  ```
 
-...
-```
+  ### Watch your Agent play
+  You can watch your agent **playing directly in your browser**
+
+  1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
+  2. Step 1: Find your model_id: RichieZou43/ppo-LunarLander-v2
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7d31595be0e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d31595be170>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d31595be200>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d31595be290>", "_build": "<function ActorCriticPolicy._build at 0x7d31595be320>", "forward": "<function ActorCriticPolicy.forward at 0x7d31595be3b0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d31595be440>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d31595be4d0>", "_predict": "<function ActorCriticPolicy._predict at 0x7d31595be560>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d31595be5f0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d31595be680>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d31595be710>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d30fe7da140>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1728309493088011588, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAMCnH75+1to9l+szu/m8Kr7TuCK9wQ67uwAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.00044800000000000395, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 3908, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.4.1+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
+{"default_settings": null, "behaviors": {"Huggy": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 200000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 15, "even_checkpoints": false, "max_steps": 2000000, "time_horizon": 1000, "summary_freq": 50000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Huggy/Huggy", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Huggy2", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,79 @@
+default_settings: null
+behaviors:
+  Huggy:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 200000
+    network_settings:
+      normalize: true
+      hidden_units: 512
+      num_layers: 3
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.995
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+    init_path: null
+    keep_checkpoints: 15
+    even_checkpoints: false
+    max_steps: 2000000
+    time_horizon: 1000
+    summary_freq: 50000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./trained-envs-executables/linux/Huggy/Huggy
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: Huggy2
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,294 @@
+Mono path[0] = '/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/Managed'
+Mono config path = '/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
+PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/Huggy
+Unable to load player prefs
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+FMOD initialized on nosound output
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.101 seconds
+ERROR: Shader Hidden/Universal Render Pipeline/Blit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/CopyDepth shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/ScreenSpaceShadows shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/Sampling shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/LutBuilderLdr shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/LutBuilderHdr shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/UberPost shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Hidden/Universal Render Pipeline/FallbackError' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Hidden/Universal Render Pipeline/FallbackError shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Hidden/Universal Render Pipeline/FallbackError' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Hidden/Universal Render Pipeline/Stop NaN shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/SubpixelMorphologicalAntialiasing shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/GaussianDepthOfField shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/BokehDepthOfField shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/CameraMotionBlur shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/PaniniProjection shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/Bloom shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/FinalPost shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Hidden/Universal Render Pipeline/StencilDeferred' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'Hidden/Universal Render Pipeline/StencilDeferred' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Hidden/Universal Render Pipeline/LensFlareDataDriven shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/Scaling Setup shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/Edge Adaptive Spatial Upsampling shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/Debug/DebugReplacement shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/kMotion/CameraMotionVectors shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/kMotion/ObjectMotionVectors shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Universal Render Pipeline/Lit' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Universal Render Pipeline/Lit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Universal Render Pipeline/Lit' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+UnloadTime: 0.843858 ms
+requesting resize 84 x 84
+Setting up 1 worker threads for Enlighten.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [4.0 KB-8.0 KB]: 26762 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 3.6 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 144 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 296.0 KB
+      Peak Allocated Bytes 211.5 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 269
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.4 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 26763 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 23.6 MB
+      Peak Large allocation bytes 16.0 MB
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [1.0 MB-2.0 MB]: 1 frames, [2.0 MB-4.0 MB]: 26762 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.3 MB
+      Peak Large allocation bytes 0 B
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.4 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 26762 frames, [64.0 KB-128.0 KB]: 1 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 65.6 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [64.0 KB-128.0 KB]: 26763 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 81.8 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.4 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [1.0 MB-2.0 MB]: 26762 frames, [16.0 MB-32.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 30.6 MB
+      Peak Large allocation bytes 24.9 MB
+    [ALLOC_CACHEOBJECTS_THREAD]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 26762 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.6 MB
+      Peak Large allocation bytes 0 B
+[ALLOC_TYPETREE] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.4 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 26763 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.0 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_TYPETREE_THREAD]
+      Peak usage frame count: [4.0 KB-8.0 KB]: 26763 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 7.3 KB
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -0,0 +1,362 @@
+{
+    "name": "root",
+    "gauges": {
+        "Huggy.Policy.Entropy.mean": {
+            "value": 1.4060325622558594,
+            "min": 1.4060325622558594,
+            "max": 1.4284539222717285,
+            "count": 40
+        },
+        "Huggy.Policy.Entropy.sum": {
+            "value": 69701.25,
+            "min": 67578.3515625,
+            "max": 77964.9140625,
+            "count": 40
+        },
+        "Huggy.Environment.EpisodeLength.mean": {
+            "value": 102.51882845188284,
+            "min": 93.53584905660378,
+            "max": 395.03937007874015,
+            "count": 40
+        },
+        "Huggy.Environment.EpisodeLength.sum": {
+            "value": 49004.0,
+            "min": 49004.0,
+            "max": 50170.0,
+            "count": 40
+        },
+        "Huggy.Step.mean": {
+            "value": 1999958.0,
+            "min": 49927.0,
+            "max": 1999958.0,
+            "count": 40
+        },
+        "Huggy.Step.sum": {
+            "value": 1999958.0,
+            "min": 49927.0,
+            "max": 1999958.0,
+            "count": 40
+        },
+        "Huggy.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 2.399282693862915,
+            "min": 0.08004207164049149,
+            "max": 2.408642530441284,
+            "count": 40
+        },
+        "Huggy.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 1146.857177734375,
+            "min": 10.085301399230957,
+            "max": 1237.6595458984375,
+            "count": 40
+        },
+        "Huggy.Environment.CumulativeReward.mean": {
+            "value": 3.6527095957031808,
+            "min": 1.7569249288903341,
+            "max": 3.9145565438114738,
+            "count": 40
+        },
+        "Huggy.Environment.CumulativeReward.sum": {
+            "value": 1745.9951867461205,
+            "min": 221.3725410401821,
+            "max": 2039.8837641477585,
+            "count": 40
+        },
+        "Huggy.Policy.ExtrinsicReward.mean": {
+            "value": 3.6527095957031808,
+            "min": 1.7569249288903341,
+            "max": 3.9145565438114738,
+            "count": 40
+        },
+        "Huggy.Policy.ExtrinsicReward.sum": {
+            "value": 1745.9951867461205,
+            "min": 221.3725410401821,
+            "max": 2039.8837641477585,
+            "count": 40
+        },
+        "Huggy.Losses.PolicyLoss.mean": {
+            "value": 0.015740701847244055,
+            "min": 0.012139983836217047,
+            "max": 0.021949149492138532,
+            "count": 40
+        },
+        "Huggy.Losses.PolicyLoss.sum": {
+            "value": 0.03148140369448811,
+            "min": 0.024279967672434094,
+            "max": 0.057927462887406966,
+            "count": 40
+        },
+        "Huggy.Losses.ValueLoss.mean": {
+            "value": 0.05115690436214208,
+            "min": 0.02265295550848047,
+            "max": 0.054528150045209466,
+            "count": 40
+        },
+        "Huggy.Losses.ValueLoss.sum": {
+            "value": 0.10231380872428417,
+            "min": 0.04530591101696094,
+            "max": 0.1635844501356284,
+            "count": 40
+        },
+        "Huggy.Policy.LearningRate.mean": {
+            "value": 4.407473530874998e-06,
+            "min": 4.407473530874998e-06,
+            "max": 0.00029535855154715,
+            "count": 40
+        },
+        "Huggy.Policy.LearningRate.sum": {
+            "value": 8.814947061749996e-06,
+            "min": 8.814947061749996e-06,
+            "max": 0.00084408586863805,
+            "count": 40
+        },
+        "Huggy.Policy.Epsilon.mean": {
+            "value": 0.101469125,
+            "min": 0.101469125,
+            "max": 0.19845284999999996,
+            "count": 40
+        },
+        "Huggy.Policy.Epsilon.sum": {
+            "value": 0.20293825,
+            "min": 0.20293825,
+            "max": 0.58136195,
+            "count": 40
+        },
+        "Huggy.Policy.Beta.mean": {
+            "value": 8.330933749999996e-05,
+            "min": 8.330933749999996e-05,
+            "max": 0.004922797215,
+            "count": 40
+        },
+        "Huggy.Policy.Beta.sum": {
+            "value": 0.00016661867499999993,
+            "min": 0.00016661867499999993,
+            "max": 0.014069961305,
+            "count": 40
+        },
+        "Huggy.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 40
+        },
+        "Huggy.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 40
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1728381353",
+        "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.4.1+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1728384162"
+    },
+    "total": 2808.3554575350004,
+    "count": 1,
+    "self": 0.4769961210004112,
+    "children": {
+        "run_training.setup": {
+            "total": 0.06083626099996309,
+            "count": 1,
+            "self": 0.06083626099996309
+        },
+        "TrainerController.start_learning": {
+            "total": 2807.817625153,
+            "count": 1,
+            "self": 5.37814837894075,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.6343449859999737,
+                    "count": 1,
+                    "self": 2.6343449859999737
+                },
+                "TrainerController.advance": {
+                    "total": 2799.688013601059,
+                    "count": 231728,
+                    "self": 5.166785613134834,
+                    "children": {
+                        "env_step": {
+                            "total": 2260.8169732760116,
+                            "count": 231728,
+                            "self": 1794.1112475828643,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 463.26255443112166,
+                                    "count": 231728,
+                                    "self": 17.625224235103815,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 445.63733019601784,
+                                            "count": 223026,
+                                            "self": 445.63733019601784
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 3.4431712620256576,
+                                    "count": 231728,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 2799.6816917849783,
+                                            "count": 231728,
+                                            "is_parallel": true,
+                                            "self": 1344.4832316809916,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.000886997999941741,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00023778199999924254,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0006492159999424985,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0006492159999424985
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.03090844799999104,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0004103719999193345,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0001875430000382039,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0001875430000382039
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.02953075200002786,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.02953075200002786
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0007797810000056415,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00019165099990914314,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0005881300000964984,
+                                                                            "count": 2,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0005881300000964984
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1455.1984601039867,
+                                                    "count": 231727,
+                                                    "is_parallel": true,
+                                                    "self": 43.40528830198173,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 90.43119397606051,
+                                                            "count": 231727,
+                                                            "is_parallel": true,
+                                                            "self": 90.43119397606051
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1220.3314303599605,
+                                                            "count": 231727,
+                                                            "is_parallel": true,
+                                                            "self": 1220.3314303599605
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 101.03054746598389,
+                                                            "count": 231727,
+                                                            "is_parallel": true,
+                                                            "self": 35.874597762046506,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 65.15594970393738,
+                                                                    "count": 463454,
+                                                                    "is_parallel": true,
+                                                                    "self": 65.15594970393738
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 533.7042547119128,
+                            "count": 231728,
+                            "self": 7.787053558869161,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 174.1971255850449,
+                                    "count": 231728,
+                                    "self": 172.70422562604494,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 1.492899958999942,
+                                            "count": 10,
+                                            "self": 1.492899958999942
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 351.7200755679987,
+                                    "count": 96,
+                                    "self": 282.06658861898995,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 69.65348694900877,
+                                            "count": 2880,
+                                            "self": 69.65348694900877
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.0690000635804608e-06,
+                    "count": 1,
+                    "self": 1.0690000635804608e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.11711711799989644,
+                    "count": 1,
+                    "self": 0.0018316069999855245,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.11528551099991091,
+                            "count": 1,
+                            "self": 0.11528551099991091
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,119 @@
+{
+    "Huggy": {
+        "checkpoints": [
+            {
+                "steps": 199890,
+                "file_path": "results/Huggy2/Huggy/Huggy-199890.onnx",
+                "reward": 3.4100904019910896,
+                "creation_time": 1728381635.2005656,
+                "auxillary_file_paths": [
+                    "results/Huggy2/Huggy/Huggy-199890.pt"
+                ]
+            },
+            {
+                "steps": 399944,
+                "file_path": "results/Huggy2/Huggy/Huggy-399944.onnx",
+                "reward": 3.631527413295794,
+                "creation_time": 1728381916.843755,
+                "auxillary_file_paths": [
+                    "results/Huggy2/Huggy/Huggy-399944.pt"
+                ]
+            },
+            {
+                "steps": 599900,
+                "file_path": "results/Huggy2/Huggy/Huggy-599900.onnx",
+                "reward": 4.301233148574829,
+                "creation_time": 1728382207.226038,
+                "auxillary_file_paths": [
+                    "results/Huggy2/Huggy/Huggy-599900.pt"
+                ]
+            },
+            {
+                "steps": 799968,
+                "file_path": "results/Huggy2/Huggy/Huggy-799968.onnx",
+                "reward": 3.8450998257658333,
+                "creation_time": 1728382490.303193,
+                "auxillary_file_paths": [
+                    "results/Huggy2/Huggy/Huggy-799968.pt"
+                ]
+            },
+            {
+                "steps": 999884,
+                "file_path": "results/Huggy2/Huggy/Huggy-999884.onnx",
+                "reward": 3.7254538614059163,
+                "creation_time": 1728382768.6166363,
+                "auxillary_file_paths": [
+                    "results/Huggy2/Huggy/Huggy-999884.pt"
+                ]
+            },
+            {
+                "steps": 1199966,
+                "file_path": "results/Huggy2/Huggy/Huggy-1199966.onnx",
+                "reward": 3.936573428767068,
+                "creation_time": 1728383060.0181613,
+                "auxillary_file_paths": [
+                    "results/Huggy2/Huggy/Huggy-1199966.pt"
+                ]
+            },
+            {
+                "steps": 1399994,
+                "file_path": "results/Huggy2/Huggy/Huggy-1399994.onnx",
+                "reward": 3.5465557500720024,
+                "creation_time": 1728383343.213567,
+                "auxillary_file_paths": [
+                    "results/Huggy2/Huggy/Huggy-1399994.pt"
+                ]
+            },
+            {
+                "steps": 1599572,
+                "file_path": "results/Huggy2/Huggy/Huggy-1599572.onnx",
+                "reward": 3.7668876876001773,
+                "creation_time": 1728383626.404749,
+                "auxillary_file_paths": [
+                    "results/Huggy2/Huggy/Huggy-1599572.pt"
+                ]
+            },
+            {
+                "steps": 1799988,
+                "file_path": "results/Huggy2/Huggy/Huggy-1799988.onnx",
+                "reward": 3.8659352949687413,
+                "creation_time": 1728383890.4169254,
+                "auxillary_file_paths": [
+                    "results/Huggy2/Huggy/Huggy-1799988.pt"
+                ]
+            },
+            {
+                "steps": 1999958,
+                "file_path": "results/Huggy2/Huggy/Huggy-1999958.onnx",
+                "reward": 3.614776133539829,
+                "creation_time": 1728384161.6996176,
+                "auxillary_file_paths": [
+                    "results/Huggy2/Huggy/Huggy-1999958.pt"
+                ]
+            },
+            {
+                "steps": 2000059,
+                "file_path": "results/Huggy2/Huggy/Huggy-2000059.onnx",
+                "reward": 3.6264866234133484,
+                "creation_time": 1728384161.821717,
+                "auxillary_file_paths": [
+                    "results/Huggy2/Huggy/Huggy-2000059.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 2000059,
+            "file_path": "results/Huggy2/Huggy.onnx",
+            "reward": 3.6264866234133484,
+            "creation_time": 1728384161.821717,
+            "auxillary_file_paths": [
+                "results/Huggy2/Huggy/Huggy-2000059.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.4.1+cu121"
+    }
+}