{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4054845571517944, "min": 1.4054845571517944, "max": 1.4287519454956055, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70029.671875, "min": 69009.0390625, "max": 77202.734375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 83.3108108108108, "min": 81.29440789473684, "max": 395.70866141732284, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49320.0, "min": 49008.0, "max": 50425.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999927.0, "min": 49997.0, "max": 1999927.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999927.0, "min": 49997.0, "max": 1999927.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.39267635345459, "min": 0.1352735012769699, "max": 2.480125904083252, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1416.46435546875, "min": 17.04446029663086, "max": 1433.6197509765625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6301688014252766, "min": 1.824407601049022, "max": 4.008000241437919, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2149.0599304437637, "min": 229.87535773217678, "max": 2279.3952461481094, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6301688014252766, "min": 1.824407601049022, "max": 4.008000241437919, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2149.0599304437637, "min": 229.87535773217678, "max": 2279.3952461481094, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016121400644381844, "min": 0.014027713015093469, "max": 0.020018055834225376, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04836420193314553, "min": 0.028055426030186938, "max": 0.05738152582198382, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05154457477231821, "min": 0.021452974590162436, "max": 0.06284252324452003, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15463372431695463, "min": 0.04290594918032487, "max": 0.17265062605341275, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.5568988143999943e-06, "min": 3.5568988143999943e-06, "max": 0.000295342126552625, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0670696443199983e-05, "min": 1.0670696443199983e-05, "max": 0.0008439256686914499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10118559999999999, "min": 0.10118559999999999, "max": 0.19844737500000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30355679999999996, "min": 0.20750564999999999, "max": 0.58130855, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.916143999999989e-05, "min": 6.916143999999989e-05, "max": 0.0049225240124999995, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020748431999999966, "min": 0.00020748431999999966, "max": 0.014067296644999998, "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": "1786185637", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1786188451" }, "total": 2814.058877254, "count": 1, "self": 0.4359396950003429, "children": { "run_training.setup": { "total": 0.02667279099989628, "count": 1, "self": 0.02667279099989628 }, "TrainerController.start_learning": { "total": 2813.596264768, "count": 1, "self": 4.996223280176309, "children": { "TrainerController._reset_env": { "total": 2.9208428379999987, "count": 1, "self": 2.9208428379999987 }, "TrainerController.advance": { "total": 2805.578981041823, "count": 232441, "self": 4.874777593848648, "children": { "env_step": { "total": 2300.276434488013, "count": 232441, "self": 1854.210504086821, "children": { "SubprocessEnvManager._take_step": { "total": 442.9254776211884, "count": 232441, "self": 16.599856230181786, "children": { "TorchPolicy.evaluate": { "total": 426.3256213910066, "count": 222989, "self": 426.3256213910066 } } }, "workers": { "total": 3.1404527800035567, "count": 232441, "self": 0.0, "children": { "worker_root": { "total": 2799.607708916108, "count": 232441, "is_parallel": true, "self": 1307.5649644301043, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008804399999462476, "count": 1, "is_parallel": true, "self": 0.0002331619999722534, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006472779999739942, "count": 2, "is_parallel": true, "self": 0.0006472779999739942 } } }, "UnityEnvironment.step": { "total": 0.03287933699994028, "count": 1, "is_parallel": true, "self": 0.0003886550000515854, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021106099995904515, "count": 1, "is_parallel": true, "self": 0.00021106099995904515 }, "communicator.exchange": { "total": 0.03150469799993516, "count": 1, "is_parallel": true, "self": 0.03150469799993516 }, "steps_from_proto": { "total": 0.0007749229999944873, "count": 1, "is_parallel": true, "self": 0.00021471299999120674, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005602100000032806, "count": 2, "is_parallel": true, "self": 0.0005602100000032806 } } } } } } }, "UnityEnvironment.step": { "total": 1492.0427444860038, "count": 232440, "is_parallel": true, "self": 40.55271519421103, "children": { "UnityEnvironment._generate_step_input": { "total": 87.9554432259672, "count": 232440, "is_parallel": true, "self": 87.9554432259672 }, "communicator.exchange": { "total": 1265.7394624618885, "count": 232440, "is_parallel": true, "self": 1265.7394624618885 }, "steps_from_proto": { "total": 97.79512360393699, "count": 232440, "is_parallel": true, "self": 34.857572377052975, "children": { "_process_rank_one_or_two_observation": { "total": 62.93755122688401, "count": 464880, "is_parallel": true, "self": 62.93755122688401 } } } } } } } } } } }, "trainer_advance": { "total": 500.42776895996144, "count": 232441, "self": 7.497252206014537, "children": { "process_trajectory": { "total": 169.98519961294812, "count": 232441, "self": 168.8823693339482, "children": { "RLTrainer._checkpoint": { "total": 1.1028302789999316, "count": 10, "self": 1.1028302789999316 } } }, "_update_policy": { "total": 322.9453171409988, "count": 97, "self": 257.20658763799895, "children": { "TorchPPOOptimizer.update": { "total": 65.73872950299983, "count": 2910, "self": 65.73872950299983 } } } } } } }, "trainer_threads": { "total": 9.840000529948156e-07, "count": 1, "self": 9.840000529948156e-07 }, "TrainerController._save_models": { "total": 0.10021662400004061, "count": 1, "self": 0.0012394969999149907, "children": { "RLTrainer._checkpoint": { "total": 0.09897712700012562, "count": 1, "self": 0.09897712700012562 } } } } } } }