{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4054110050201416, "min": 1.4054110050201416, "max": 1.429377794265747, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68858.109375, "min": 68503.0234375, "max": 77207.140625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 96.94891944990177, "min": 90.80580762250453, "max": 386.4076923076923, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49347.0, "min": 49135.0, "max": 50233.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999987.0, "min": 49613.0, "max": 1999987.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999987.0, "min": 49613.0, "max": 1999987.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3611257076263428, "min": 0.10773203521966934, "max": 2.3942618370056152, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1201.81298828125, "min": 13.897432327270508, "max": 1265.7779541015625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.568800626662953, "min": 1.8797889393429423, "max": 3.8050702598518478, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1816.5195189714432, "min": 242.49277317523956, "max": 2020.9404296278954, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.568800626662953, "min": 1.8797889393429423, "max": 3.8050702598518478, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1816.5195189714432, "min": 242.49277317523956, "max": 2020.9404296278954, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.014514267695873667, "min": 0.013040203665150329, "max": 0.018777419557833734, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.043542803087621, "min": 0.026080407330300658, "max": 0.055620715143110525, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04717978733695216, "min": 0.021219974321623643, "max": 0.06652765180915594, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14153936201085648, "min": 0.04243994864324729, "max": 0.19186905746658645, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.354748881783349e-06, "min": 3.354748881783349e-06, "max": 0.00029534385155205, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0064246645350047e-05, "min": 1.0064246645350047e-05, "max": 0.000844113018629, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10111821666666666, "min": 0.10111821666666666, "max": 0.19844795000000007, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30335465, "min": 0.20739645, "max": 0.5813710000000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.579901166666693e-05, "min": 6.579901166666693e-05, "max": 0.0049225527049999995, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001973970350000008, "min": 0.0001973970350000008, "max": 0.0140704129, "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": "1671129962", "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": "1671132198" }, "total": 2236.575288321, "count": 1, "self": 0.4250415899996369, "children": { "run_training.setup": { "total": 0.19209313099963765, "count": 1, "self": 0.19209313099963765 }, "TrainerController.start_learning": { "total": 2235.9581536000005, "count": 1, "self": 3.9271696471432733, "children": { "TrainerController._reset_env": { "total": 6.283443952999733, "count": 1, "self": 6.283443952999733 }, "TrainerController.advance": { "total": 2225.6320693338575, "count": 231646, "self": 4.0993883839555565, "children": { "env_step": { "total": 1756.6033290098067, "count": 231646, "self": 1476.9736896221584, "children": { "SubprocessEnvManager._take_step": { "total": 276.97410639487316, "count": 231646, "self": 14.520571924592332, "children": { "TorchPolicy.evaluate": { "total": 262.45353447028083, "count": 222886, "self": 65.3211424224437, "children": { "TorchPolicy.sample_actions": { "total": 197.13239204783713, "count": 222886, "self": 197.13239204783713 } } } } }, "workers": { "total": 2.655532992775079, "count": 231646, "self": 0.0, "children": { "worker_root": { "total": 2227.990001239792, "count": 231646, "is_parallel": true, "self": 1015.0165200837437, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000916241000595619, "count": 1, "is_parallel": true, "self": 0.0003486200012048357, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005676209993907833, "count": 2, "is_parallel": true, "self": 0.0005676209993907833 } } }, "UnityEnvironment.step": { "total": 0.03177868199963996, "count": 1, "is_parallel": true, "self": 0.0003305510008431156, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001912079997055116, "count": 1, "is_parallel": true, "self": 0.0001912079997055116 }, "communicator.exchange": { "total": 0.030340489999616693, "count": 1, "is_parallel": true, "self": 0.030340489999616693 }, "steps_from_proto": { "total": 0.0009164329994746367, "count": 1, "is_parallel": true, "self": 0.000451258999419224, "children": { "_process_rank_one_or_two_observation": { "total": 0.00046517400005541276, "count": 2, "is_parallel": true, "self": 0.00046517400005541276 } } } } } } }, "UnityEnvironment.step": { "total": 1212.9734811560484, "count": 231645, "is_parallel": true, "self": 34.51443620223654, "children": { "UnityEnvironment._generate_step_input": { "total": 81.35980136408398, "count": 231645, "is_parallel": true, "self": 81.35980136408398 }, "communicator.exchange": { "total": 1000.4043888567076, "count": 231645, "is_parallel": true, "self": 1000.4043888567076 }, "steps_from_proto": { "total": 96.69485473302029, "count": 231645, "is_parallel": true, "self": 42.07582720388655, "children": { "_process_rank_one_or_two_observation": { "total": 54.619027529133746, "count": 463290, "is_parallel": true, "self": 54.619027529133746 } } } } } } } } } } }, "trainer_advance": { "total": 464.92935194009533, "count": 231646, "self": 6.1129546045112875, "children": { "process_trajectory": { "total": 148.77196356157947, "count": 231646, "self": 147.56950853657963, "children": { "RLTrainer._checkpoint": { "total": 1.2024550249998356, "count": 10, "self": 1.2024550249998356 } } }, "_update_policy": { "total": 310.0444337740046, "count": 97, "self": 257.4537282680103, "children": { "TorchPPOOptimizer.update": { "total": 52.590705505994265, "count": 2910, "self": 52.590705505994265 } } } } } } }, "trainer_threads": { "total": 1.178000275103841e-06, "count": 1, "self": 1.178000275103841e-06 }, "TrainerController._save_models": { "total": 0.11546948799968959, "count": 1, "self": 0.0019029559989576228, "children": { "RLTrainer._checkpoint": { "total": 0.11356653200073197, "count": 1, "self": 0.11356653200073197 } } } } } } }