{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3396919965744019, "min": 1.3396919965744019, "max": 1.4231895208358765, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 67164.1171875, "min": 66159.8515625, "max": 77452.2421875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 91.13805970149254, "min": 87.70744680851064, "max": 416.2916666666667, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48850.0, "min": 48752.0, "max": 50215.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999998.0, "min": 49668.0, "max": 1999998.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999998.0, "min": 49668.0, "max": 1999998.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3546128273010254, "min": 0.10830855369567871, "max": 2.4244518280029297, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1262.072509765625, "min": 12.888717651367188, "max": 1282.5350341796875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7084678589408075, "min": 1.8965367155165231, "max": 3.8441950390415807, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1987.738772392273, "min": 225.68786914646626, "max": 2019.5158308148384, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7084678589408075, "min": 1.8965367155165231, "max": 3.8441950390415807, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1987.738772392273, "min": 225.68786914646626, "max": 2019.5158308148384, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.0352586105953642, "min": 0.029927996995237613, "max": 0.03776442667225549, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.1057758317860926, "min": 0.059855993990475226, "max": 0.11146210751135593, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04331915584956639, "min": 0.01845995400752115, "max": 0.04331915584956639, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.12995746754869916, "min": 0.0369199080150423, "max": 0.12995746754869916, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.306398897900005e-06, "min": 3.306398897900005e-06, "max": 0.000295337926554025, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.919196693700015e-06, "min": 9.919196693700015e-06, "max": 0.00084414856861715, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10110209999999999, "min": 0.10110209999999999, "max": 0.198445975, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3033063, "min": 0.20740765, "max": 0.58138285, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.49947900000001e-05, "min": 6.49947900000001e-05, "max": 0.004922454152500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001949843700000003, "min": 0.0001949843700000003, "max": 0.014071004215000002, "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": "1677587374", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "1.22.4", "end_time_seconds": "1677589736" }, "total": 2362.083476327, "count": 1, "self": 0.4471877500000119, "children": { "run_training.setup": { "total": 0.1800357229999463, "count": 1, "self": 0.1800357229999463 }, "TrainerController.start_learning": { "total": 2361.456252854, "count": 1, "self": 3.9220285698743282, "children": { "TrainerController._reset_env": { "total": 10.658186169999908, "count": 1, "self": 10.658186169999908 }, "TrainerController.advance": { "total": 2346.7604816851263, "count": 231689, "self": 4.19326119993093, "children": { "env_step": { "total": 1780.8497863282141, "count": 231689, "self": 1485.323019997162, "children": { "SubprocessEnvManager._take_step": { "total": 292.81256266000617, "count": 231689, "self": 15.202925918056508, "children": { "TorchPolicy.evaluate": { "total": 277.60963674194966, "count": 222966, "self": 69.30677834691767, "children": { "TorchPolicy.sample_actions": { "total": 208.302858395032, "count": 222966, "self": 208.302858395032 } } } } }, "workers": { "total": 2.7142036710459934, "count": 231689, "self": 0.0, "children": { "worker_root": { "total": 2353.4525832120935, "count": 231689, "is_parallel": true, "self": 1150.6393507961184, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0039053149999972447, "count": 1, "is_parallel": true, "self": 0.0004829420000760365, "children": { "_process_rank_one_or_two_observation": { "total": 0.0034223729999212082, "count": 2, "is_parallel": true, "self": 0.0034223729999212082 } } }, "UnityEnvironment.step": { "total": 0.028384008000102767, "count": 1, "is_parallel": true, "self": 0.0002892350000820443, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008020369999712784, "count": 1, "is_parallel": true, "self": 0.0008020369999712784 }, "communicator.exchange": { "total": 0.026608866000060516, "count": 1, "is_parallel": true, "self": 0.026608866000060516 }, "steps_from_proto": { "total": 0.0006838699999889286, "count": 1, "is_parallel": true, "self": 0.00023303299997223803, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004508370000166906, "count": 2, "is_parallel": true, "self": 0.0004508370000166906 } } } } } } }, "UnityEnvironment.step": { "total": 1202.813232415975, "count": 231688, "is_parallel": true, "self": 37.18651032895377, "children": { "UnityEnvironment._generate_step_input": { "total": 77.6731327681897, "count": 231688, "is_parallel": true, "self": 77.6731327681897 }, "communicator.exchange": { "total": 999.5812674528777, "count": 231688, "is_parallel": true, "self": 999.5812674528777 }, "steps_from_proto": { "total": 88.37232186595384, "count": 231688, "is_parallel": true, "self": 35.73312397684799, "children": { "_process_rank_one_or_two_observation": { "total": 52.639197889105844, "count": 463376, "is_parallel": true, "self": 52.639197889105844 } } } } } } } } } } }, "trainer_advance": { "total": 561.7174341569813, "count": 231689, "self": 6.4528503200458545, "children": { "process_trajectory": { "total": 156.74116302793607, "count": 231689, "self": 155.4845420269363, "children": { "RLTrainer._checkpoint": { "total": 1.2566210009997576, "count": 10, "self": 1.2566210009997576 } } }, "_update_policy": { "total": 398.5234208089994, "count": 97, "self": 292.35684811599344, "children": { "TorchPPOOptimizer.update": { "total": 106.16657269300595, "count": 11895, "self": 106.16657269300595 } } } } } } }, "trainer_threads": { "total": 8.469996828353032e-07, "count": 1, "self": 8.469996828353032e-07 }, "TrainerController._save_models": { "total": 0.11555558200006999, "count": 1, "self": 0.0020191360003991576, "children": { "RLTrainer._checkpoint": { "total": 0.11353644599967083, "count": 1, "self": 0.11353644599967083 } } } } } } }