{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4028276205062866, "min": 1.4028276205062866, "max": 1.426146388053894, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69735.9609375, "min": 68696.953125, "max": 76566.703125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 99.068, "min": 81.73553719008264, "max": 396.63492063492066, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49534.0, "min": 49236.0, "max": 49976.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999997.0, "min": 49989.0, "max": 1999997.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999997.0, "min": 49989.0, "max": 1999997.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3969130516052246, "min": 0.06284072995185852, "max": 2.4694459438323975, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1198.45654296875, "min": 7.855091571807861, "max": 1464.737060546875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5379013612270356, "min": 1.857462304353714, "max": 3.98543688480617, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1768.9506806135178, "min": 232.18278804421425, "max": 2315.0689674019814, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5379013612270356, "min": 1.857462304353714, "max": 3.98543688480617, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1768.9506806135178, "min": 232.18278804421425, "max": 2315.0689674019814, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015502174489342402, "min": 0.013723477651202149, "max": 0.02136158649227582, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04650652346802721, "min": 0.027446955302404298, "max": 0.05563260692870244, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.049569168976611566, "min": 0.022972435110972984, "max": 0.06296835113316775, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1487075069298347, "min": 0.046046937070786956, "max": 0.18516006159285703, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.486548837850008e-06, "min": 3.486548837850008e-06, "max": 0.0002953356015548, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0459646513550024e-05, "min": 1.0459646513550024e-05, "max": 0.0008440308186563999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10116215000000002, "min": 0.10116215000000002, "max": 0.19844520000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3034864500000001, "min": 0.20745455000000002, "max": 0.5813436000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.799128500000013e-05, "min": 6.799128500000013e-05, "max": 0.00492241548, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020397385500000039, "min": 0.00020397385500000039, "max": 0.014069045640000003, "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": "1726417792", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1726420404" }, "total": 2612.003500327, "count": 1, "self": 0.4345275419996142, "children": { "run_training.setup": { "total": 0.059454344000073434, "count": 1, "self": 0.059454344000073434 }, "TrainerController.start_learning": { "total": 2611.509518441, "count": 1, "self": 4.656345241022336, "children": { "TrainerController._reset_env": { "total": 2.439727566999977, "count": 1, "self": 2.439727566999977 }, "TrainerController.advance": { "total": 2604.290350808978, "count": 232573, "self": 4.810721937107246, "children": { "env_step": { "total": 2076.650089941891, "count": 232573, "self": 1640.5037841209396, "children": { "SubprocessEnvManager._take_step": { "total": 433.08918961596, "count": 232573, "self": 16.326614944993707, "children": { "TorchPolicy.evaluate": { "total": 416.7625746709663, "count": 223001, "self": 416.7625746709663 } } }, "workers": { "total": 3.057116204991644, "count": 232573, "self": 0.0, "children": { "worker_root": { "total": 2604.00725320507, "count": 232573, "is_parallel": true, "self": 1275.3757122771367, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011102760000767375, "count": 1, "is_parallel": true, "self": 0.00037041700011286594, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007398589999638716, "count": 2, "is_parallel": true, "self": 0.0007398589999638716 } } }, "UnityEnvironment.step": { "total": 0.03284953900003984, "count": 1, "is_parallel": true, "self": 0.0005063499999096166, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021888900005251344, "count": 1, "is_parallel": true, "self": 0.00021888900005251344 }, "communicator.exchange": { "total": 0.031228449000082037, "count": 1, "is_parallel": true, "self": 0.031228449000082037 }, "steps_from_proto": { "total": 0.0008958509999956732, "count": 1, "is_parallel": true, "self": 0.00028227300003891287, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006135779999567603, "count": 2, "is_parallel": true, "self": 0.0006135779999567603 } } } } } } }, "UnityEnvironment.step": { "total": 1328.6315409279332, "count": 232572, "is_parallel": true, "self": 39.17254286008142, "children": { "UnityEnvironment._generate_step_input": { "total": 87.87266476887271, "count": 232572, "is_parallel": true, "self": 87.87266476887271 }, "communicator.exchange": { "total": 1107.759753772033, "count": 232572, "is_parallel": true, "self": 1107.759753772033 }, "steps_from_proto": { "total": 93.82657952694603, "count": 232572, "is_parallel": true, "self": 35.731528897921635, "children": { "_process_rank_one_or_two_observation": { "total": 58.0950506290244, "count": 465144, "is_parallel": true, "self": 58.0950506290244 } } } } } } } } } } }, "trainer_advance": { "total": 522.8295389299794, "count": 232573, "self": 6.626725503921307, "children": { "process_trajectory": { "total": 170.0985410910571, "count": 232573, "self": 168.841086514057, "children": { "RLTrainer._checkpoint": { "total": 1.2574545770000896, "count": 10, "self": 1.2574545770000896 } } }, "_update_policy": { "total": 346.10427233500104, "count": 97, "self": 278.90165930600244, "children": { "TorchPPOOptimizer.update": { "total": 67.2026130289986, "count": 2910, "self": 67.2026130289986 } } } } } } }, "trainer_threads": { "total": 9.979999049392063e-07, "count": 1, "self": 9.979999049392063e-07 }, "TrainerController._save_models": { "total": 0.12309382600005847, "count": 1, "self": 0.003123944999970263, "children": { "RLTrainer._checkpoint": { "total": 0.11996988100008821, "count": 1, "self": 0.11996988100008821 } } } } } } }