{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4093185663223267, "min": 1.4093185663223267, "max": 1.4272563457489014, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 73092.8984375, "min": 69107.0078125, "max": 77333.25, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 91.27490774907749, "min": 89.00360360360361, "max": 387.9153846153846, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49471.0, "min": 48914.0, "max": 50429.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999944.0, "min": 49809.0, "max": 1999944.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999944.0, "min": 49809.0, "max": 1999944.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.419072389602661, "min": 0.00958615355193615, "max": 2.439077138900757, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1311.13720703125, "min": 1.2366137504577637, "max": 1311.13720703125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7381561400705596, "min": 1.772560828762461, "max": 3.9004807517080025, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2026.0806279182434, "min": 228.66034691035748, "max": 2053.7334114313126, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7381561400705596, "min": 1.772560828762461, "max": 3.9004807517080025, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2026.0806279182434, "min": 228.66034691035748, "max": 2053.7334114313126, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.0161419063428184, "min": 0.01355804536882109, "max": 0.02244327056929857, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0484257190284552, "min": 0.02711609073764218, "max": 0.056642567843664435, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05495168914397558, "min": 0.021450175158679485, "max": 0.05495168914397558, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16485506743192674, "min": 0.04290035031735897, "max": 0.16485506743192674, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.177748940783333e-06, "min": 3.177748940783333e-06, "max": 0.0002953600515466501, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.533246822349999e-06, "min": 9.533246822349999e-06, "max": 0.0008442249185916999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10105921666666669, "min": 0.10105921666666669, "max": 0.19845334999999997, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3031776500000001, "min": 0.207261, "max": 0.5814083, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.285491166666666e-05, "min": 6.285491166666666e-05, "max": 0.004922822165, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00018856473499999997, "min": 0.00018856473499999997, "max": 0.01407227417, "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": "1718776456", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718778889" }, "total": 2432.767641677, "count": 1, "self": 0.448486032999881, "children": { "run_training.setup": { "total": 0.05620966399999361, "count": 1, "self": 0.05620966399999361 }, "TrainerController.start_learning": { "total": 2432.26294598, "count": 1, "self": 4.8048909760887, "children": { "TrainerController._reset_env": { "total": 3.1900022879999597, "count": 1, "self": 3.1900022879999597 }, "TrainerController.advance": { "total": 2424.1574436179117, "count": 231402, "self": 5.0157411318105005, "children": { "env_step": { "total": 1923.213785679105, "count": 231402, "self": 1583.3257635620985, "children": { "SubprocessEnvManager._take_step": { "total": 336.8911151589407, "count": 231402, "self": 18.777335756823618, "children": { "TorchPolicy.evaluate": { "total": 318.1137794021171, "count": 223087, "self": 318.1137794021171 } } }, "workers": { "total": 2.9969069580658925, "count": 231402, "self": 0.0, "children": { "worker_root": { "total": 2424.968213460958, "count": 231402, "is_parallel": true, "self": 1158.1434132899963, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009158089999345975, "count": 1, "is_parallel": true, "self": 0.0002337910000278498, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006820179999067477, "count": 2, "is_parallel": true, "self": 0.0006820179999067477 } } }, "UnityEnvironment.step": { "total": 0.03134932199998275, "count": 1, "is_parallel": true, "self": 0.0004057480000483338, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002172599999994418, "count": 1, "is_parallel": true, "self": 0.0002172599999994418 }, "communicator.exchange": { "total": 0.029956001999948967, "count": 1, "is_parallel": true, "self": 0.029956001999948967 }, "steps_from_proto": { "total": 0.0007703119999860064, "count": 1, "is_parallel": true, "self": 0.00021021500003826077, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005600969999477456, "count": 2, "is_parallel": true, "self": 0.0005600969999477456 } } } } } } }, "UnityEnvironment.step": { "total": 1266.8248001709617, "count": 231401, "is_parallel": true, "self": 39.404633659117735, "children": { "UnityEnvironment._generate_step_input": { "total": 80.01100519497072, "count": 231401, "is_parallel": true, "self": 80.01100519497072 }, "communicator.exchange": { "total": 1056.7447172990517, "count": 231401, "is_parallel": true, "self": 1056.7447172990517 }, "steps_from_proto": { "total": 90.66444401782167, "count": 231401, "is_parallel": true, "self": 31.813355147873494, "children": { "_process_rank_one_or_two_observation": { "total": 58.85108886994817, "count": 462802, "is_parallel": true, "self": 58.85108886994817 } } } } } } } } } } }, "trainer_advance": { "total": 495.9279168069962, "count": 231402, "self": 7.525372064973453, "children": { "process_trajectory": { "total": 150.16832792102184, "count": 231402, "self": 148.8735526030224, "children": { "RLTrainer._checkpoint": { "total": 1.294775317999438, "count": 10, "self": 1.294775317999438 } } }, "_update_policy": { "total": 338.2342168210009, "count": 97, "self": 272.4965198359871, "children": { "TorchPPOOptimizer.update": { "total": 65.73769698501383, "count": 2910, "self": 65.73769698501383 } } } } } } }, "trainer_threads": { "total": 1.3609997040475719e-06, "count": 1, "self": 1.3609997040475719e-06 }, "TrainerController._save_models": { "total": 0.11060773700000937, "count": 1, "self": 0.0019464580000203568, "children": { "RLTrainer._checkpoint": { "total": 0.10866127899998901, "count": 1, "self": 0.10866127899998901 } } } } } } }