{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4038785696029663, "min": 1.4038784503936768, "max": 1.42717444896698, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71242.625, "min": 68659.2578125, "max": 76460.5625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 83.20840336134454, "min": 72.21929824561404, "max": 398.015873015873, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49509.0, "min": 49036.0, "max": 50150.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999453.0, "min": 49945.0, "max": 1999453.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999453.0, "min": 49945.0, "max": 1999453.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4830198287963867, "min": 0.09279413521289825, "max": 2.5366086959838867, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1477.3968505859375, "min": 11.59926700592041, "max": 1660.500732421875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.718119429039354, "min": 1.83930166387558, "max": 4.051991121872291, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2212.2810602784157, "min": 229.91270798444748, "max": 2617.5862647295, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.718119429039354, "min": 1.83930166387558, "max": 4.051991121872291, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2212.2810602784157, "min": 229.91270798444748, "max": 2617.5862647295, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.020246555269437118, "min": 0.014043369677771504, "max": 0.020305014822709685, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.060739665808311354, "min": 0.028086739355543008, "max": 0.060739665808311354, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.060848127388291894, "min": 0.02208880763500929, "max": 0.06418516387542089, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18254438216487567, "min": 0.04417761527001858, "max": 0.18254438216487567, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6343487885833385e-06, "min": 3.6343487885833385e-06, "max": 0.00029534580155140004, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0903046365750015e-05, "min": 1.0903046365750015e-05, "max": 0.0008440125186625, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1012114166666667, "min": 0.1012114166666667, "max": 0.19844859999999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3036342500000001, "min": 0.20757150000000008, "max": 0.5813375000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.044969166666677e-05, "min": 7.044969166666677e-05, "max": 0.0049225851400000005, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021134907500000032, "min": 0.00021134907500000032, "max": 0.014068741250000003, "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": "1690208147", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1690210723" }, "total": 2576.5447684279998, "count": 1, "self": 0.8012442309996004, "children": { "run_training.setup": { "total": 0.03388063599999214, "count": 1, "self": 0.03388063599999214 }, "TrainerController.start_learning": { "total": 2575.709643561, "count": 1, "self": 5.004293590008729, "children": { "TrainerController._reset_env": { "total": 6.409268569999995, "count": 1, "self": 6.409268569999995 }, "TrainerController.advance": { "total": 2564.0957177769915, "count": 233290, "self": 4.792626965019281, "children": { "env_step": { "total": 1989.1924953680436, "count": 233290, "self": 1680.6447749601061, "children": { "SubprocessEnvManager._take_step": { "total": 305.3965556369153, "count": 233290, "self": 17.77076716787002, "children": { "TorchPolicy.evaluate": { "total": 287.6257884690453, "count": 223060, "self": 287.6257884690453 } } }, "workers": { "total": 3.151164771022252, "count": 233290, "self": 0.0, "children": { "worker_root": { "total": 2567.307395548982, "count": 233290, "is_parallel": true, "self": 1195.5876762210482, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008383819999835396, "count": 1, "is_parallel": true, "self": 0.00023437399994463703, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006040080000389025, "count": 2, "is_parallel": true, "self": 0.0006040080000389025 } } }, "UnityEnvironment.step": { "total": 0.047665382999980466, "count": 1, "is_parallel": true, "self": 0.0003308339998966403, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002122320000239597, "count": 1, "is_parallel": true, "self": 0.0002122320000239597 }, "communicator.exchange": { "total": 0.04637653900005034, "count": 1, "is_parallel": true, "self": 0.04637653900005034 }, "steps_from_proto": { "total": 0.0007457780000095227, "count": 1, "is_parallel": true, "self": 0.00023496799997246853, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005108100000370541, "count": 2, "is_parallel": true, "self": 0.0005108100000370541 } } } } } } }, "UnityEnvironment.step": { "total": 1371.719719327934, "count": 233289, "is_parallel": true, "self": 40.95411577506911, "children": { "UnityEnvironment._generate_step_input": { "total": 86.93277387496141, "count": 233289, "is_parallel": true, "self": 86.93277387496141 }, "communicator.exchange": { "total": 1143.1404016460067, "count": 233289, "is_parallel": true, "self": 1143.1404016460067 }, "steps_from_proto": { "total": 100.69242803189678, "count": 233289, "is_parallel": true, "self": 38.81488616300578, "children": { "_process_rank_one_or_two_observation": { "total": 61.877541868891, "count": 466578, "is_parallel": true, "self": 61.877541868891 } } } } } } } } } } }, "trainer_advance": { "total": 570.1105954439284, "count": 233290, "self": 6.581385088864067, "children": { "process_trajectory": { "total": 148.81779483606448, "count": 233290, "self": 147.30700608806382, "children": { "RLTrainer._checkpoint": { "total": 1.5107887480006639, "count": 10, "self": 1.5107887480006639 } } }, "_update_policy": { "total": 414.71141551899984, "count": 97, "self": 353.9666394819963, "children": { "TorchPPOOptimizer.update": { "total": 60.74477603700353, "count": 2910, "self": 60.74477603700353 } } } } } } }, "trainer_threads": { "total": 1.3910002962802537e-06, "count": 1, "self": 1.3910002962802537e-06 }, "TrainerController._save_models": { "total": 0.20036223299985068, "count": 1, "self": 0.002731566999500501, "children": { "RLTrainer._checkpoint": { "total": 0.19763066600035017, "count": 1, "self": 0.19763066600035017 } } } } } } }