{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4076281785964966, "min": 1.4076205492019653, "max": 1.4297053813934326, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69790.203125, "min": 68243.265625, "max": 79641.4609375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 117.86057692307692, "min": 90.7908256880734, "max": 416.15833333333336, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49030.0, "min": 49030.0, "max": 50088.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999422.0, "min": 49986.0, "max": 1999422.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999422.0, "min": 49986.0, "max": 1999422.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.2977538108825684, "min": 0.11703692376613617, "max": 2.391529083251953, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 955.8656005859375, "min": 13.927393913269043, "max": 1295.326171875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.446225574383369, "min": 1.7215617552023976, "max": 3.859749073344293, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1433.6298389434814, "min": 204.8658488690853, "max": 2030.6048892140388, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.446225574383369, "min": 1.7215617552023976, "max": 3.859749073344293, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1433.6298389434814, "min": 204.8658488690853, "max": 2030.6048892140388, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01589557842526119, "min": 0.013780716463710027, "max": 0.020347840875425995, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03179115685052238, "min": 0.027561432927420054, "max": 0.05893223676976049, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04132430919756492, "min": 0.020398248732089997, "max": 0.05952551770541403, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.08264861839512984, "min": 0.040796497464179994, "max": 0.1785765531162421, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.495298501599998e-06, "min": 4.495298501599998e-06, "max": 0.000295290076569975, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.990597003199996e-06, "min": 8.990597003199996e-06, "max": 0.0008438500687166499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10149840000000003, "min": 0.10149840000000003, "max": 0.198430025, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20299680000000006, "min": 0.20299680000000006, "max": 0.58128335, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.477015999999999e-05, "min": 8.477015999999999e-05, "max": 0.0049216582475, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00016954031999999997, "min": 0.00016954031999999997, "max": 0.014066039165000002, "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": "1691138068", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=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": "1691140681" }, "total": 2612.468989083, "count": 1, "self": 0.7900017770002705, "children": { "run_training.setup": { "total": 0.04105358200013143, "count": 1, "self": 0.04105358200013143 }, "TrainerController.start_learning": { "total": 2611.6379337239996, "count": 1, "self": 4.7937618720766295, "children": { "TrainerController._reset_env": { "total": 5.25788017800005, "count": 1, "self": 5.25788017800005 }, "TrainerController.advance": { "total": 2601.4017161939228, "count": 231108, "self": 4.93660130389253, "children": { "env_step": { "total": 2021.0054063770208, "count": 231108, "self": 1700.233383085143, "children": { "SubprocessEnvManager._take_step": { "total": 317.65738805392016, "count": 231108, "self": 17.949014513900465, "children": { "TorchPolicy.evaluate": { "total": 299.7083735400197, "count": 223024, "self": 299.7083735400197 } } }, "workers": { "total": 3.1146352379576, "count": 231108, "self": 0.0, "children": { "worker_root": { "total": 2603.191438381952, "count": 231108, "is_parallel": true, "self": 1219.3395538109385, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009681110000201443, "count": 1, "is_parallel": true, "self": 0.000285329000234924, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006827819997852203, "count": 2, "is_parallel": true, "self": 0.0006827819997852203 } } }, "UnityEnvironment.step": { "total": 0.029802587999938623, "count": 1, "is_parallel": true, "self": 0.0003783159997965413, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00024204300007113488, "count": 1, "is_parallel": true, "self": 0.00024204300007113488 }, "communicator.exchange": { "total": 0.028409672999941904, "count": 1, "is_parallel": true, "self": 0.028409672999941904 }, "steps_from_proto": { "total": 0.0007725560001290432, "count": 1, "is_parallel": true, "self": 0.00024095800017676083, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005315979999522824, "count": 2, "is_parallel": true, "self": 0.0005315979999522824 } } } } } } }, "UnityEnvironment.step": { "total": 1383.8518845710137, "count": 231107, "is_parallel": true, "self": 41.31843605990639, "children": { "UnityEnvironment._generate_step_input": { "total": 87.86542659904148, "count": 231107, "is_parallel": true, "self": 87.86542659904148 }, "communicator.exchange": { "total": 1151.9965421810668, "count": 231107, "is_parallel": true, "self": 1151.9965421810668 }, "steps_from_proto": { "total": 102.67147973099895, "count": 231107, "is_parallel": true, "self": 38.59630180000636, "children": { "_process_rank_one_or_two_observation": { "total": 64.0751779309926, "count": 462214, "is_parallel": true, "self": 64.0751779309926 } } } } } } } } } } }, "trainer_advance": { "total": 575.4597085130092, "count": 231108, "self": 7.244997430111425, "children": { "process_trajectory": { "total": 144.34875920589866, "count": 231108, "self": 142.7888198428982, "children": { "RLTrainer._checkpoint": { "total": 1.559939363000467, "count": 10, "self": 1.559939363000467 } } }, "_update_policy": { "total": 423.86595187699913, "count": 96, "self": 363.11951503200225, "children": { "TorchPPOOptimizer.update": { "total": 60.74643684499688, "count": 2880, "self": 60.74643684499688 } } } } } } }, "trainer_threads": { "total": 1.258999873243738e-06, "count": 1, "self": 1.258999873243738e-06 }, "TrainerController._save_models": { "total": 0.18457422100027543, "count": 1, "self": 0.0068675340003210295, "children": { "RLTrainer._checkpoint": { "total": 0.1777066869999544, "count": 1, "self": 0.1777066869999544 } } } } } } }