{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.406590461730957, "min": 1.406590461730957, "max": 1.4271314144134521, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71353.5234375, "min": 68739.03125, "max": 78317.1484375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 83.79491525423728, "min": 79.41639871382637, "max": 397.0079365079365, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49439.0, "min": 48730.0, "max": 50284.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999916.0, "min": 49414.0, "max": 1999916.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999916.0, "min": 49414.0, "max": 1999916.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.417358875274658, "min": 0.07471233606338501, "max": 2.4850099086761475, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1426.24169921875, "min": 9.339041709899902, "max": 1534.745361328125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6692319943743237, "min": 1.7617017402648927, "max": 3.9974654778893552, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2164.846876680851, "min": 220.21271753311157, "max": 2428.093115925789, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6692319943743237, "min": 1.7617017402648927, "max": 3.9974654778893552, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2164.846876680851, "min": 220.21271753311157, "max": 2428.093115925789, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.0162354612761798, "min": 0.013104002612211237, "max": 0.020484475717178915, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0487063838285394, "min": 0.026208005224422473, "max": 0.05604054856376024, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0594173765844769, "min": 0.02345195558543007, "max": 0.06654860706379016, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1782521297534307, "min": 0.04690391117086014, "max": 0.18137964966396491, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4069988643666796e-06, "min": 3.4069988643666796e-06, "max": 0.00029528692657102506, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0220996593100039e-05, "min": 1.0220996593100039e-05, "max": 0.0008434218188594, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10113563333333335, "min": 0.10113563333333335, "max": 0.198428975, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30340690000000003, "min": 0.20740005, "max": 0.5811406000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.666810333333355e-05, "min": 6.666810333333355e-05, "max": 0.004921605852499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020000431000000068, "min": 0.00020000431000000068, "max": 0.01405891594, "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": "1671041931", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1671044194" }, "total": 2262.8138873999997, "count": 1, "self": 0.44277089499973954, "children": { "run_training.setup": { "total": 0.10527543800003514, "count": 1, "self": 0.10527543800003514 }, "TrainerController.start_learning": { "total": 2262.265841067, "count": 1, "self": 3.8565478029458973, "children": { "TrainerController._reset_env": { "total": 9.988992580999934, "count": 1, "self": 9.988992580999934 }, "TrainerController.advance": { "total": 2248.3043743990543, "count": 232720, "self": 4.23252722525649, "children": { "env_step": { "total": 1768.114408793905, "count": 232720, "self": 1484.518075243741, "children": { "SubprocessEnvManager._take_step": { "total": 280.96532352699114, "count": 232720, "self": 14.33723976602596, "children": { "TorchPolicy.evaluate": { "total": 266.6280837609652, "count": 223006, "self": 66.00220557196906, "children": { "TorchPolicy.sample_actions": { "total": 200.62587818899613, "count": 223006, "self": 200.62587818899613 } } } } }, "workers": { "total": 2.6310100231731894, "count": 232720, "self": 0.0, "children": { "worker_root": { "total": 2254.321778588019, "count": 232720, "is_parallel": true, "self": 1034.1939830740735, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017549770000186982, "count": 1, "is_parallel": true, "self": 0.000319597000043359, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014353799999753392, "count": 2, "is_parallel": true, "self": 0.0014353799999753392 } } }, "UnityEnvironment.step": { "total": 0.026381904000004397, "count": 1, "is_parallel": true, "self": 0.00029525499996907456, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001817119999714123, "count": 1, "is_parallel": true, "self": 0.0001817119999714123 }, "communicator.exchange": { "total": 0.025218604999963645, "count": 1, "is_parallel": true, "self": 0.025218604999963645 }, "steps_from_proto": { "total": 0.0006863320001002648, "count": 1, "is_parallel": true, "self": 0.00022870600014357478, "children": { "_process_rank_one_or_two_observation": { "total": 0.00045762599995669007, "count": 2, "is_parallel": true, "self": 0.00045762599995669007 } } } } } } }, "UnityEnvironment.step": { "total": 1220.1277955139453, "count": 232719, "is_parallel": true, "self": 35.11991141495241, "children": { "UnityEnvironment._generate_step_input": { "total": 75.56463078103945, "count": 232719, "is_parallel": true, "self": 75.56463078103945 }, "communicator.exchange": { "total": 1016.0898638619673, "count": 232719, "is_parallel": true, "self": 1016.0898638619673 }, "steps_from_proto": { "total": 93.35338945598619, "count": 232719, "is_parallel": true, "self": 38.178251192118296, "children": { "_process_rank_one_or_two_observation": { "total": 55.17513826386789, "count": 465438, "is_parallel": true, "self": 55.17513826386789 } } } } } } } } } } }, "trainer_advance": { "total": 475.9574383798928, "count": 232720, "self": 6.401791535962616, "children": { "process_trajectory": { "total": 149.7276454639316, "count": 232720, "self": 149.2623151849316, "children": { "RLTrainer._checkpoint": { "total": 0.4653302789999998, "count": 4, "self": 0.4653302789999998 } } }, "_update_policy": { "total": 319.82800137999857, "count": 97, "self": 265.26530748799166, "children": { "TorchPPOOptimizer.update": { "total": 54.562693892006905, "count": 2910, "self": 54.562693892006905 } } } } } } }, "trainer_threads": { "total": 8.530000741302501e-07, "count": 1, "self": 8.530000741302501e-07 }, "TrainerController._save_models": { "total": 0.1159254310000506, "count": 1, "self": 0.0020987949997106625, "children": { "RLTrainer._checkpoint": { "total": 0.11382663600033993, "count": 1, "self": 0.11382663600033993 } } } } } } }