{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.415183663368225, "min": 1.415183663368225, "max": 1.424683928489685, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71149.7734375, "min": 68930.96875, "max": 78176.71875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 90.06375227686704, "min": 80.33224755700326, "max": 407.0243902439024, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49445.0, "min": 48936.0, "max": 50064.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999915.0, "min": 49438.0, "max": 1999915.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999915.0, "min": 49438.0, "max": 1999915.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3912031650543213, "min": -0.05532871559262276, "max": 2.491377592086792, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1312.7705078125, "min": -6.75010347366333, "max": 1472.070556640625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5944298952003644, "min": 1.8533180331597563, "max": 3.9741224895786327, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1973.3420124650002, "min": 226.10480004549026, "max": 2300.250617682934, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5944298952003644, "min": 1.8533180331597563, "max": 3.9741224895786327, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1973.3420124650002, "min": 226.10480004549026, "max": 2300.250617682934, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.023820463898462346, "min": 0.02127804233621444, "max": 0.027244250442890916, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.07146139169538704, "min": 0.04264774331046889, "max": 0.07765272695784613, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0569601627273692, "min": 0.021283635109042128, "max": 0.06663494314998389, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1708804881821076, "min": 0.042567270218084256, "max": 0.19990482944995167, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 1.2139987861000013e-06, "min": 1.2139987861000013e-06, "max": 9.844625155375e-05, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 3.641996358300004e-06, "min": 3.641996358300004e-06, "max": 0.00028133746866255006, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10121390000000001, "min": 0.10121390000000001, "max": 0.19844625000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3036417, "min": 0.20757635000000002, "max": 0.5813374499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.057361000000006e-05, "min": 7.057361000000006e-05, "max": 0.004922467875000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002117208300000002, "min": 0.0002117208300000002, "max": 0.014068738754999997, "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": "1711053405", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1711055884" }, "total": 2478.7643959290003, "count": 1, "self": 0.44245176100002936, "children": { "run_training.setup": { "total": 0.06030739199991331, "count": 1, "self": 0.06030739199991331 }, "TrainerController.start_learning": { "total": 2478.261636776, "count": 1, "self": 4.675929665975673, "children": { "TrainerController._reset_env": { "total": 3.0873448109998662, "count": 1, "self": 3.0873448109998662 }, "TrainerController.advance": { "total": 2470.364623831025, "count": 232760, "self": 4.714722488834468, "children": { "env_step": { "total": 1972.430806433039, "count": 232760, "self": 1627.9980100029295, "children": { "SubprocessEnvManager._take_step": { "total": 341.415922308129, "count": 232760, "self": 17.85505601812588, "children": { "TorchPolicy.evaluate": { "total": 323.5608662900031, "count": 223086, "self": 323.5608662900031 } } }, "workers": { "total": 3.016874121980436, "count": 232760, "self": 0.0, "children": { "worker_root": { "total": 2470.703075888042, "count": 232760, "is_parallel": true, "self": 1162.057012296974, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009500500000285683, "count": 1, "is_parallel": true, "self": 0.0002473570000347536, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007026929999938147, "count": 2, "is_parallel": true, "self": 0.0007026929999938147 } } }, "UnityEnvironment.step": { "total": 0.03313475799996013, "count": 1, "is_parallel": true, "self": 0.00042048199998134805, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023514800000157265, "count": 1, "is_parallel": true, "self": 0.00023514800000157265 }, "communicator.exchange": { "total": 0.031665753999959634, "count": 1, "is_parallel": true, "self": 0.031665753999959634 }, "steps_from_proto": { "total": 0.0008133740000175749, "count": 1, "is_parallel": true, "self": 0.00020977200006200292, "children": { "_process_rank_one_or_two_observation": { "total": 0.000603601999955572, "count": 2, "is_parallel": true, "self": 0.000603601999955572 } } } } } } }, "UnityEnvironment.step": { "total": 1308.6460635910678, "count": 232759, "is_parallel": true, "self": 40.54503151589074, "children": { "UnityEnvironment._generate_step_input": { "total": 82.99683654913952, "count": 232759, "is_parallel": true, "self": 82.99683654913952 }, "communicator.exchange": { "total": 1090.8104082539885, "count": 232759, "is_parallel": true, "self": 1090.8104082539885 }, "steps_from_proto": { "total": 94.29378727204903, "count": 232759, "is_parallel": true, "self": 33.37042866211277, "children": { "_process_rank_one_or_two_observation": { "total": 60.92335860993626, "count": 465518, "is_parallel": true, "self": 60.92335860993626 } } } } } } } } } } }, "trainer_advance": { "total": 493.2190949091514, "count": 232760, "self": 7.172102363040267, "children": { "process_trajectory": { "total": 158.72511499011284, "count": 232760, "self": 157.31587334011306, "children": { "RLTrainer._checkpoint": { "total": 1.4092416499997853, "count": 10, "self": 1.4092416499997853 } } }, "_update_policy": { "total": 327.3218775559983, "count": 97, "self": 252.70024011000555, "children": { "TorchPPOOptimizer.update": { "total": 74.62163744599275, "count": 5820, "self": 74.62163744599275 } } } } } } }, "trainer_threads": { "total": 1.0230000953015406e-06, "count": 1, "self": 1.0230000953015406e-06 }, "TrainerController._save_models": { "total": 0.13373744499995155, "count": 1, "self": 0.00272885899994435, "children": { "RLTrainer._checkpoint": { "total": 0.1310085860000072, "count": 1, "self": 0.1310085860000072 } } } } } } }