{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4041913747787476, "min": 1.4041913747787476, "max": 1.4263631105422974, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70884.984375, "min": 68039.0859375, "max": 77350.46875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 87.99466192170819, "min": 80.80844155844156, "max": 390.421875, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49453.0, "min": 48860.0, "max": 50112.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999976.0, "min": 49893.0, "max": 1999976.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999976.0, "min": 49893.0, "max": 1999976.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3769569396972656, "min": 0.1308751255273819, "max": 2.4956512451171875, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1335.849853515625, "min": 16.62114143371582, "max": 1502.23046875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5563603461425077, "min": 1.5774890339280676, "max": 3.9713607452533863, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1998.6745145320892, "min": 200.3411073088646, "max": 2385.201385140419, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5563603461425077, "min": 1.5774890339280676, "max": 3.9713607452533863, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1998.6745145320892, "min": 200.3411073088646, "max": 2385.201385140419, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01822112857027807, "min": 0.014481107703735082, "max": 0.020890536647493716, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05466338571083421, "min": 0.028962215407470165, "max": 0.06267160994248115, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.051620578517516454, "min": 0.022365308946205514, "max": 0.0588115028416117, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15486173555254937, "min": 0.04562431536614895, "max": 0.17182650603353977, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.1073489642499955e-06, "min": 3.1073489642499955e-06, "max": 0.00029527282657572493, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.322046892749986e-06, "min": 9.322046892749986e-06, "max": 0.0008436078187974, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10103575, "min": 0.10103575, "max": 0.19842427499999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30310725, "min": 0.20723620000000004, "max": 0.5812025999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.168392499999993e-05, "min": 6.168392499999993e-05, "max": 0.0049213713225000014, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001850517749999998, "min": 0.0001850517749999998, "max": 0.014062009739999999, "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": "1678412739", "python_version": "3.7.12 | packaged by conda-forge | (default, Oct 26 2021, 06:08:53) \n[GCC 9.4.0]", "command_line_arguments": "/opt/conda/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": "1678415262" }, "total": 2522.3744960500003, "count": 1, "self": 0.4470319440001731, "children": { "run_training.setup": { "total": 0.8185758229999465, "count": 1, "self": 0.8185758229999465 }, "TrainerController.start_learning": { "total": 2521.108888283, "count": 1, "self": 5.1364645529661175, "children": { "TrainerController._reset_env": { "total": 11.063574672999948, "count": 1, "self": 11.063574672999948 }, "TrainerController.advance": { "total": 2504.7765936390333, "count": 232527, "self": 5.675897545138923, "children": { "env_step": { "total": 1923.214885028968, "count": 232527, "self": 1627.6621679819427, "children": { "SubprocessEnvManager._take_step": { "total": 292.32450297098273, "count": 232527, "self": 16.761738311973204, "children": { "TorchPolicy.evaluate": { "total": 275.56276465900953, "count": 223016, "self": 70.556916851138, "children": { "TorchPolicy.sample_actions": { "total": 205.00584780787153, "count": 223016, "self": 205.00584780787153 } } } } }, "workers": { "total": 3.228214076042377, "count": 232527, "self": 0.0, "children": { "worker_root": { "total": 2512.971206812014, "count": 232527, "is_parallel": true, "self": 1199.2943019959966, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011113900000054855, "count": 1, "is_parallel": true, "self": 0.000440019999928154, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006713700000773315, "count": 2, "is_parallel": true, "self": 0.0006713700000773315 } } }, "UnityEnvironment.step": { "total": 0.032379192000007606, "count": 1, "is_parallel": true, "self": 0.0004136149999567351, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002157840000336364, "count": 1, "is_parallel": true, "self": 0.0002157840000336364 }, "communicator.exchange": { "total": 0.030825746000004983, "count": 1, "is_parallel": true, "self": 0.030825746000004983 }, "steps_from_proto": { "total": 0.0009240470000122514, "count": 1, "is_parallel": true, "self": 0.0002854880000313642, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006385589999808872, "count": 2, "is_parallel": true, "self": 0.0006385589999808872 } } } } } } }, "UnityEnvironment.step": { "total": 1313.6769048160172, "count": 232526, "is_parallel": true, "self": 43.926322693825114, "children": { "UnityEnvironment._generate_step_input": { "total": 91.34207595419105, "count": 232526, "is_parallel": true, "self": 91.34207595419105 }, "communicator.exchange": { "total": 1069.0602515119674, "count": 232526, "is_parallel": true, "self": 1069.0602515119674 }, "steps_from_proto": { "total": 109.34825465603342, "count": 232526, "is_parallel": true, "self": 47.16165120601977, "children": { "_process_rank_one_or_two_observation": { "total": 62.18660345001365, "count": 465052, "is_parallel": true, "self": 62.18660345001365 } } } } } } } } } } }, "trainer_advance": { "total": 575.8858110649264, "count": 232527, "self": 7.567275873970175, "children": { "process_trajectory": { "total": 193.17929839395674, "count": 232527, "self": 191.77902218595682, "children": { "RLTrainer._checkpoint": { "total": 1.400276207999923, "count": 10, "self": 1.400276207999923 } } }, "_update_policy": { "total": 375.1392367969995, "count": 97, "self": 328.21412148800846, "children": { "TorchPPOOptimizer.update": { "total": 46.92511530899105, "count": 2910, "self": 46.92511530899105 } } } } } } }, "trainer_threads": { "total": 1.5680002434237394e-06, "count": 1, "self": 1.5680002434237394e-06 }, "TrainerController._save_models": { "total": 0.13225385000032475, "count": 1, "self": 0.002864193000277737, "children": { "RLTrainer._checkpoint": { "total": 0.129389657000047, "count": 1, "self": 0.129389657000047 } } } } } } }