{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8897051811218262, "min": 0.8897051811218262, "max": 2.8569395542144775, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8514.478515625, "min": 8514.478515625, "max": 29257.91796875, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.457656860351562, "min": 0.3489009439945221, "max": 12.46760368347168, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2429.2431640625, "min": 67.68678283691406, "max": 2543.39111328125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06260161505091602, "min": 0.06091816015952431, "max": 0.07273314488679627, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2504064602036641, "min": 0.24367264063809724, "max": 0.3636657244339814, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2096359972641164, "min": 0.13142130117721892, "max": 0.2912275382116729, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8385439890564657, "min": 0.5256852047088757, "max": 1.3266321219065609, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.136363636363637, "min": 3.9318181818181817, "max": 24.581818181818182, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1062.0, "min": 173.0, "max": 1352.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.136363636363637, "min": 3.9318181818181817, "max": 24.581818181818182, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1062.0, "min": 173.0, "max": 1352.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679710908", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1679711384" }, "total": 475.5439805289999, "count": 1, "self": 0.4322393349999629, "children": { "run_training.setup": { "total": 0.11167632899991986, "count": 1, "self": 0.11167632899991986 }, "TrainerController.start_learning": { "total": 475.000064865, "count": 1, "self": 0.5673002990023406, "children": { "TrainerController._reset_env": { "total": 10.890072292000013, "count": 1, "self": 10.890072292000013 }, "TrainerController.advance": { "total": 463.39215905599747, "count": 18204, "self": 0.28085731799922087, "children": { "env_step": { "total": 463.11130173799825, "count": 18204, "self": 333.7272600219943, "children": { "SubprocessEnvManager._take_step": { "total": 129.10844565400532, "count": 18204, "self": 2.487105667020728, "children": { "TorchPolicy.evaluate": { "total": 126.6213399869846, "count": 18204, "self": 126.6213399869846 } } }, "workers": { "total": 0.27559606199861264, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 473.4284616000193, "count": 18204, "is_parallel": true, "self": 226.64217325803713, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005151245999968523, "count": 1, "is_parallel": true, "self": 0.003602536999892436, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015487090000760872, "count": 10, "is_parallel": true, "self": 0.0015487090000760872 } } }, "UnityEnvironment.step": { "total": 0.03520089400001325, "count": 1, "is_parallel": true, "self": 0.0005735259999255504, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041485200006263767, "count": 1, "is_parallel": true, "self": 0.00041485200006263767 }, "communicator.exchange": { "total": 0.03229982599998493, "count": 1, "is_parallel": true, "self": 0.03229982599998493 }, "steps_from_proto": { "total": 0.0019126900000401292, "count": 1, "is_parallel": true, "self": 0.0003827190000720293, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015299709999681, "count": 10, "is_parallel": true, "self": 0.0015299709999681 } } } } } } }, "UnityEnvironment.step": { "total": 246.78628834198219, "count": 18203, "is_parallel": true, "self": 9.497267092998868, "children": { "UnityEnvironment._generate_step_input": { "total": 5.394609682000578, "count": 18203, "is_parallel": true, "self": 5.394609682000578 }, "communicator.exchange": { "total": 199.54631191999783, "count": 18203, "is_parallel": true, "self": 199.54631191999783 }, "steps_from_proto": { "total": 32.348099646984906, "count": 18203, "is_parallel": true, "self": 6.512505657976476, "children": { "_process_rank_one_or_two_observation": { "total": 25.83559398900843, "count": 182030, "is_parallel": true, "self": 25.83559398900843 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015986300013537402, "count": 1, "self": 0.00015986300013537402, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 459.8879108639886, "count": 421757, "is_parallel": true, "self": 10.287233287882032, "children": { "process_trajectory": { "total": 255.58675832410722, "count": 421757, "is_parallel": true, "self": 254.2480978221073, "children": { "RLTrainer._checkpoint": { "total": 1.3386605019999251, "count": 4, "is_parallel": true, "self": 1.3386605019999251 } } }, "_update_policy": { "total": 194.01391925199937, "count": 90, "is_parallel": true, "self": 72.01887266399694, "children": { "TorchPPOOptimizer.update": { "total": 121.99504658800242, "count": 4584, "is_parallel": true, "self": 121.99504658800242 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1503733550000561, "count": 1, "self": 0.001436402000081216, "children": { "RLTrainer._checkpoint": { "total": 0.1489369529999749, "count": 1, "self": 0.1489369529999749 } } } } } } }