{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.399888277053833, "min": 1.399888277053833, "max": 1.4249364137649536, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70439.578125, "min": 68025.015625, "max": 78359.828125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 89.08648648648649, "min": 77.79179810725552, "max": 377.9398496240602, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49443.0, "min": 49186.0, "max": 50266.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999995.0, "min": 49987.0, "max": 1999995.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999995.0, "min": 49987.0, "max": 1999995.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4492268562316895, "min": -0.03878455609083176, "max": 2.50095272064209, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1359.3209228515625, "min": -5.119561195373535, "max": 1559.0411376953125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6885050519092664, "min": 1.678141678034356, "max": 3.990134831192424, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2047.1203038096428, "min": 221.514701500535, "max": 2429.2083029150963, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6885050519092664, "min": 1.678141678034356, "max": 3.990134831192424, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2047.1203038096428, "min": 221.514701500535, "max": 2429.2083029150963, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016264450806193053, "min": 0.014489772990850724, "max": 0.01853118933051721, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.048793352418579156, "min": 0.028979545981701448, "max": 0.05559356799155163, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05981135422156917, "min": 0.024115596959988276, "max": 0.06136278249323368, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17943406266470752, "min": 0.04823119391997655, "max": 0.17943406266470752, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.717248760950002e-06, "min": 3.717248760950002e-06, "max": 0.0002953394265535249, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1151746282850006e-05, "min": 1.1151746282850006e-05, "max": 0.0008439634686788499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10123905000000001, "min": 0.10123905000000001, "max": 0.19844647499999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30371715000000005, "min": 0.20761515000000003, "max": 0.5813211499999998, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.182859500000004e-05, "min": 7.182859500000004e-05, "max": 0.0049224791025, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021548578500000013, "min": 0.00021548578500000013, "max": 0.014067925385000003, "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": "1670772507", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=SweHuggy --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": "1670774728" }, "total": 2220.980603321, "count": 1, "self": 0.4019460409999738, "children": { "run_training.setup": { "total": 0.10921331299999792, "count": 1, "self": 0.10921331299999792 }, "TrainerController.start_learning": { "total": 2220.469443967, "count": 1, "self": 3.825907915027983, "children": { "TrainerController._reset_env": { "total": 10.307026213999961, "count": 1, "self": 10.307026213999961 }, "TrainerController.advance": { "total": 2206.227799740973, "count": 232965, "self": 4.215903987997535, "children": { "env_step": { "total": 1733.091290446005, "count": 232965, "self": 1454.540573806047, "children": { "SubprocessEnvManager._take_step": { "total": 275.9247874609812, "count": 232965, "self": 14.118936214034989, "children": { "TorchPolicy.evaluate": { "total": 261.8058512469462, "count": 223048, "self": 66.35848251999442, "children": { "TorchPolicy.sample_actions": { "total": 195.44736872695177, "count": 223048, "self": 195.44736872695177 } } } } }, "workers": { "total": 2.625929178976776, "count": 232965, "self": 0.0, "children": { "worker_root": { "total": 2212.4539407389984, "count": 232965, "is_parallel": true, "self": 1018.6113009570088, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025853409999854193, "count": 1, "is_parallel": true, "self": 0.00038607400000501, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021992669999804093, "count": 2, "is_parallel": true, "self": 0.0021992669999804093 } } }, "UnityEnvironment.step": { "total": 0.02780279699999255, "count": 1, "is_parallel": true, "self": 0.00027512400004070514, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022170900001583504, "count": 1, "is_parallel": true, "self": 0.00022170900001583504 }, "communicator.exchange": { "total": 0.0265645309999627, "count": 1, "is_parallel": true, "self": 0.0265645309999627 }, "steps_from_proto": { "total": 0.0007414329999733127, "count": 1, "is_parallel": true, "self": 0.0002761039999654713, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004653290000078414, "count": 2, "is_parallel": true, "self": 0.0004653290000078414 } } } } } } }, "UnityEnvironment.step": { "total": 1193.8426397819896, "count": 232964, "is_parallel": true, "self": 34.988119229893755, "children": { "UnityEnvironment._generate_step_input": { "total": 79.8569980800674, "count": 232964, "is_parallel": true, "self": 79.8569980800674 }, "communicator.exchange": { "total": 983.3842635060485, "count": 232964, "is_parallel": true, "self": 983.3842635060485 }, "steps_from_proto": { "total": 95.61325896598015, "count": 232964, "is_parallel": true, "self": 41.543777267871974, "children": { "_process_rank_one_or_two_observation": { "total": 54.06948169810818, "count": 465928, "is_parallel": true, "self": 54.06948169810818 } } } } } } } } } } }, "trainer_advance": { "total": 468.9206053069705, "count": 232965, "self": 5.934655194934692, "children": { "process_trajectory": { "total": 152.4199962580371, "count": 232965, "self": 151.95543200903734, "children": { "RLTrainer._checkpoint": { "total": 0.4645642489997499, "count": 4, "self": 0.4645642489997499 } } }, "_update_policy": { "total": 310.56595385399874, "count": 97, "self": 258.6435466170029, "children": { "TorchPPOOptimizer.update": { "total": 51.92240723699581, "count": 2910, "self": 51.92240723699581 } } } } } } }, "trainer_threads": { "total": 8.849997357174288e-07, "count": 1, "self": 8.849997357174288e-07 }, "TrainerController._save_models": { "total": 0.10870921199966688, "count": 1, "self": 0.001905475000057777, "children": { "RLTrainer._checkpoint": { "total": 0.1068037369996091, "count": 1, "self": 0.1068037369996091 } } } } } } }