{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.401330590248108, "min": 1.401330590248108, "max": 1.4247760772705078, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70491.1328125, "min": 69189.7421875, "max": 77476.4375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 85.9791304347826, "min": 80.0211038961039, "max": 371.6296296296296, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49438.0, "min": 48782.0, "max": 50170.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999989.0, "min": 49604.0, "max": 1999989.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999989.0, "min": 49604.0, "max": 1999989.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.501140594482422, "min": 0.03814518451690674, "max": 2.501140594482422, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1438.1558837890625, "min": 5.111454963684082, "max": 1509.0037841796875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.947512558543164, "min": 1.7071644975178277, "max": 3.9886813824160945, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2269.819721162319, "min": 228.76004266738892, "max": 2401.186192214489, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.947512558543164, "min": 1.7071644975178277, "max": 3.9886813824160945, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2269.819721162319, "min": 228.76004266738892, "max": 2401.186192214489, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01538786309457565, "min": 0.013837453970578888, "max": 0.019332321415519497, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04616358928372695, "min": 0.027674907941157775, "max": 0.05528875629339988, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05355617408123281, "min": 0.023229650190720957, "max": 0.06185802121957144, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16066852224369843, "min": 0.046459300381441915, "max": 0.18557406365871432, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.847948717383331e-06, "min": 3.847948717383331e-06, "max": 0.000295315876561375, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1543846152149993e-05, "min": 1.1543846152149993e-05, "max": 0.00084428296857235, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10128261666666666, "min": 0.10128261666666666, "max": 0.19843862499999992, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30384785, "min": 0.20769395, "max": 0.5814276499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.400257166666663e-05, "min": 7.400257166666663e-05, "max": 0.0049220873874999994, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022200771499999988, "min": 0.00022200771499999988, "max": 0.014073239735, "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": "1727621030", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1727623547" }, "total": 2516.510173906, "count": 1, "self": 0.440732578999814, "children": { "run_training.setup": { "total": 0.05578214100000878, "count": 1, "self": 0.05578214100000878 }, "TrainerController.start_learning": { "total": 2516.013659186, "count": 1, "self": 4.638922223064583, "children": { "TrainerController._reset_env": { "total": 2.375399401999971, "count": 1, "self": 2.375399401999971 }, "TrainerController.advance": { "total": 2508.888772500936, "count": 232672, "self": 4.67954438292918, "children": { "env_step": { "total": 1993.1169637359362, "count": 232672, "self": 1570.4455423118409, "children": { "SubprocessEnvManager._take_step": { "total": 419.73412117503494, "count": 232672, "self": 16.271085228969355, "children": { "TorchPolicy.evaluate": { "total": 403.4630359460656, "count": 222976, "self": 403.4630359460656 } } }, "workers": { "total": 2.9373002490603994, "count": 232672, "self": 0.0, "children": { "worker_root": { "total": 2508.543002719932, "count": 232672, "is_parallel": true, "self": 1238.1057899768377, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008471799999369978, "count": 1, "is_parallel": true, "self": 0.00023808299988559156, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006090970000514062, "count": 2, "is_parallel": true, "self": 0.0006090970000514062 } } }, "UnityEnvironment.step": { "total": 0.04359673199996905, "count": 1, "is_parallel": true, "self": 0.0006202209999628394, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023281699998278782, "count": 1, "is_parallel": true, "self": 0.00023281699998278782 }, "communicator.exchange": { "total": 0.04196260700007315, "count": 1, "is_parallel": true, "self": 0.04196260700007315 }, "steps_from_proto": { "total": 0.0007810869999502756, "count": 1, "is_parallel": true, "self": 0.0002119689999062757, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005691180000439999, "count": 2, "is_parallel": true, "self": 0.0005691180000439999 } } } } } } }, "UnityEnvironment.step": { "total": 1270.437212743094, "count": 232671, "is_parallel": true, "self": 38.12549754986753, "children": { "UnityEnvironment._generate_step_input": { "total": 83.53103203001433, "count": 232671, "is_parallel": true, "self": 83.53103203001433 }, "communicator.exchange": { "total": 1057.7425486590832, "count": 232671, "is_parallel": true, "self": 1057.7425486590832 }, "steps_from_proto": { "total": 91.03813450412883, "count": 232671, "is_parallel": true, "self": 34.25619670822857, "children": { "_process_rank_one_or_two_observation": { "total": 56.78193779590026, "count": 465342, "is_parallel": true, "self": 56.78193779590026 } } } } } } } } } } }, "trainer_advance": { "total": 511.0922643820704, "count": 232672, "self": 6.53427338910717, "children": { "process_trajectory": { "total": 170.29594084096175, "count": 232672, "self": 168.98898133496175, "children": { "RLTrainer._checkpoint": { "total": 1.3069595059999983, "count": 10, "self": 1.3069595059999983 } } }, "_update_policy": { "total": 334.2620501520015, "count": 97, "self": 267.2505244010007, "children": { "TorchPPOOptimizer.update": { "total": 67.01152575100082, "count": 2910, "self": 67.01152575100082 } } } } } } }, "trainer_threads": { "total": 9.79000105871819e-07, "count": 1, "self": 9.79000105871819e-07 }, "TrainerController._save_models": { "total": 0.11056408099966575, "count": 1, "self": 0.0018821519993252878, "children": { "RLTrainer._checkpoint": { "total": 0.10868192900034046, "count": 1, "self": 0.10868192900034046 } } } } } } }