{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4045618772506714, "min": 1.4045618772506714, "max": 1.4291884899139404, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70799.75, "min": 68890.4609375, "max": 78007.71875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 92.5749063670412, "min": 81.53553719008265, "max": 400.584, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49435.0, "min": 49149.0, "max": 50122.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999961.0, "min": 49776.0, "max": 1999961.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999961.0, "min": 49776.0, "max": 1999961.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3829185962677, "min": 0.036440931260585785, "max": 2.442204236984253, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1272.478515625, "min": 4.518675327301025, "max": 1466.570556640625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6581810424836836, "min": 1.92474329447554, "max": 3.9658922989619896, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1953.468676686287, "min": 238.66816851496696, "max": 2318.376360118389, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6581810424836836, "min": 1.92474329447554, "max": 3.9658922989619896, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1953.468676686287, "min": 238.66816851496696, "max": 2318.376360118389, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01709298083207816, "min": 0.012725892418529838, "max": 0.01938430511460562, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05127894249623448, "min": 0.025451784837059677, "max": 0.057729656699423995, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.053835299362738925, "min": 0.0240155881891648, "max": 0.06281582166751226, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16150589808821678, "min": 0.0480311763783296, "max": 0.18844746500253678, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.5487488171166758e-06, "min": 3.5487488171166758e-06, "max": 0.00029536530154489996, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0646246451350028e-05, "min": 1.0646246451350028e-05, "max": 0.0008442091685969498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10118288333333336, "min": 0.10118288333333336, "max": 0.19845510000000005, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3035486500000001, "min": 0.20749595000000004, "max": 0.5814030500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.90258783333335e-05, "min": 6.90258783333335e-05, "max": 0.00492290949, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020707763500000048, "min": 0.00020707763500000048, "max": 0.014072012194999999, "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": "1672038525", "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": "1672040881" }, "total": 2356.316210146, "count": 1, "self": 0.43927228299980925, "children": { "run_training.setup": { "total": 0.11421333399999867, "count": 1, "self": 0.11421333399999867 }, "TrainerController.start_learning": { "total": 2355.762724529, "count": 1, "self": 3.961137758014047, "children": { "TrainerController._reset_env": { "total": 9.767841917999988, "count": 1, "self": 9.767841917999988 }, "TrainerController.advance": { "total": 2341.911276410986, "count": 232048, "self": 4.191503512968666, "children": { "env_step": { "total": 1842.5933339340258, "count": 232048, "self": 1552.41775907605, "children": { "SubprocessEnvManager._take_step": { "total": 287.4579074270172, "count": 232048, "self": 15.209896114091066, "children": { "TorchPolicy.evaluate": { "total": 272.2480113129261, "count": 223021, "self": 67.700040016005, "children": { "TorchPolicy.sample_actions": { "total": 204.5479712969211, "count": 223021, "self": 204.5479712969211 } } } } }, "workers": { "total": 2.7176674309585565, "count": 232048, "self": 0.0, "children": { "worker_root": { "total": 2347.6242551190153, "count": 232048, "is_parallel": true, "self": 1071.3202156510204, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002389055999969969, "count": 1, "is_parallel": true, "self": 0.0003653279999866754, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020237279999832936, "count": 2, "is_parallel": true, "self": 0.0020237279999832936 } } }, "UnityEnvironment.step": { "total": 0.050986517000012554, "count": 1, "is_parallel": true, "self": 0.00031972099998256454, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018566400001418515, "count": 1, "is_parallel": true, "self": 0.00018566400001418515 }, "communicator.exchange": { "total": 0.04972647499999994, "count": 1, "is_parallel": true, "self": 0.04972647499999994 }, "steps_from_proto": { "total": 0.0007546570000158681, "count": 1, "is_parallel": true, "self": 0.00026012099999661586, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004945360000192522, "count": 2, "is_parallel": true, "self": 0.0004945360000192522 } } } } } } }, "UnityEnvironment.step": { "total": 1276.304039467995, "count": 232047, "is_parallel": true, "self": 36.320098051045306, "children": { "UnityEnvironment._generate_step_input": { "total": 79.73894362395691, "count": 232047, "is_parallel": true, "self": 79.73894362395691 }, "communicator.exchange": { "total": 1062.5312170680304, "count": 232047, "is_parallel": true, "self": 1062.5312170680304 }, "steps_from_proto": { "total": 97.71378072496236, "count": 232047, "is_parallel": true, "self": 39.866146799956994, "children": { "_process_rank_one_or_two_observation": { "total": 57.84763392500537, "count": 464094, "is_parallel": true, "self": 57.84763392500537 } } } } } } } } } } }, "trainer_advance": { "total": 495.12643896399135, "count": 232048, "self": 6.329463074920341, "children": { "process_trajectory": { "total": 155.80979657307046, "count": 232048, "self": 154.13521218507094, "children": { "RLTrainer._checkpoint": { "total": 1.6745843879995164, "count": 10, "self": 1.6745843879995164 } } }, "_update_policy": { "total": 332.98717931600055, "count": 97, "self": 278.29191855399284, "children": { "TorchPPOOptimizer.update": { "total": 54.695260762007706, "count": 2910, "self": 54.695260762007706 } } } } } } }, "trainer_threads": { "total": 9.949999366654083e-07, "count": 1, "self": 9.949999366654083e-07 }, "TrainerController._save_models": { "total": 0.1224674469999627, "count": 1, "self": 0.0025382799999533745, "children": { "RLTrainer._checkpoint": { "total": 0.11992916700000933, "count": 1, "self": 0.11992916700000933 } } } } } } }