Push agent to the Hub

README.md

@@ -0,0 +1,29 @@
+---
+tags:
+- LunarLander-v2
+- ppo
+- deep-reinforcement-learning
+- reinforcement-learning
+- custom-implementation
+- deep-rl-course
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: -217.07 +/- 95.29
+      name: mean_reward
+      verified: false
+---
+
+# PPO Agent Playing LunarLander-v2
+
+This is a trained model of a PPO agent playing LunarLander-v2.
+
+# Hyperparameters

logs/events.out.tfevents.1690496744.ptah.14495.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1067ce2f5944decf5050549a18773aea2981cf1b2b5cc1d512ab65631c32dad6
+size 109982

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cee5ad18540ca27371d88f93ced12fe09b0eb7491d8e7a8f892883dd7a135cd
+size 42597

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -217.06841832451164, "std_reward": 95.28960418118031, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-28T00:26:19.721627"}