{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0946364402770996, "min": 1.0928155183792114, "max": 2.2952566146850586, "count": 16 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10571.9990234375, "min": 10571.9990234375, "max": 21262.677734375, "count": 16 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 49936.0, "max": 199984.0, "count": 16 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 49936.0, "max": 199984.0, "count": 16 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 11.663004875183105, "min": 4.613474369049072, "max": 11.663004875183105, "count": 16 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2390.916015625, "min": 415.2126770019531, "max": 2390.916015625, "count": 16 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 16 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 4378.0, "max": 10945.0, "count": 16 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06690535414617282, "min": 0.0629664167288366, "max": 0.08164551496441823, "count": 16 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3345267707308641, "min": 0.16329102992883646, "max": 0.37080980874780634, "count": 16 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20293266107054317, "min": 0.20219451240172573, "max": 0.2816235404826847, "count": 16 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.0146633053527159, "min": 0.4996212343776635, "max": 1.321066310008367, "count": 16 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.620097459999994e-06, "min": 7.620097459999994e-06, "max": 0.00022707002430999998, "count": 16 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.810048729999997e-05, "min": 3.810048729999997e-05, "max": 0.0010116001628000001, "count": 16 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10254, "min": 0.10254, "max": 0.17569, "count": 16 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5127, "min": 0.35138, "max": 0.8371999999999999, "count": 16 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001367459999999999, "min": 0.0001367459999999999, "max": 0.0037869310000000008, "count": 16 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0006837299999999995, "min": 0.0006837299999999995, "max": 0.01687628, "count": 16 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 23.29090909090909, "min": 11.363636363636363, "max": 23.29090909090909, "count": 16 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1281.0, "min": 250.0, "max": 1281.0, "count": 16 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.29090909090909, "min": 11.363636363636363, "max": 23.29090909090909, "count": 16 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1281.0, "min": 250.0, "max": 1281.0, "count": 16 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678982457", "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 --resume", "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": "1678982815" }, "total": 357.5105299379993, "count": 1, "self": 0.4229530849988805, "children": { "run_training.setup": { "total": 0.10437413999989076, "count": 1, "self": 0.10437413999989076 }, "TrainerController.start_learning": { "total": 356.98320271300054, "count": 1, "self": 0.42532609600129945, "children": { "TrainerController._reset_env": { "total": 5.815293917000417, "count": 1, "self": 5.815293917000417 }, "TrainerController.advance": { "total": 350.609135067999, "count": 14076, "self": 0.2169891020112118, "children": { "env_step": { "total": 350.39214596598777, "count": 14076, "self": 254.35593229293045, "children": { "SubprocessEnvManager._take_step": { "total": 95.8235493300399, "count": 14076, "self": 1.5876107260501158, "children": { "TorchPolicy.evaluate": { "total": 94.23593860398978, "count": 14076, "self": 94.23593860398978 } } }, "workers": { "total": 0.21266434301742265, "count": 14076, "self": 0.0, "children": { "worker_root": { "total": 355.8562420690605, "count": 14076, "is_parallel": true, "self": 167.9133230540965, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019935740001528757, "count": 1, "is_parallel": true, "self": 0.0006973040008233511, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012962699993295246, "count": 10, "is_parallel": true, "self": 0.0012962699993295246 } } }, "UnityEnvironment.step": { "total": 0.04526850700040086, "count": 1, "is_parallel": true, "self": 0.0004340719997344422, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00028055500024493085, "count": 1, "is_parallel": true, "self": 0.00028055500024493085 }, "communicator.exchange": { "total": 0.04302806400028203, "count": 1, "is_parallel": true, "self": 0.04302806400028203 }, "steps_from_proto": { "total": 0.0015258160001394572, "count": 1, "is_parallel": true, "self": 0.0003153769985146937, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012104390016247635, "count": 10, "is_parallel": true, "self": 0.0012104390016247635 } } } } } } }, "UnityEnvironment.step": { "total": 187.942919014964, "count": 14075, "is_parallel": true, "self": 7.318242229825955, "children": { "UnityEnvironment._generate_step_input": { "total": 3.949933673029591, "count": 14075, "is_parallel": true, "self": 3.949933673029591 }, "communicator.exchange": { "total": 152.8487242990468, "count": 14075, "is_parallel": true, "self": 152.8487242990468 }, "steps_from_proto": { "total": 23.826018813061637, "count": 14075, "is_parallel": true, "self": 4.675390604853419, "children": { "_process_rank_one_or_two_observation": { "total": 19.150628208208218, "count": 140750, "is_parallel": true, "self": 19.150628208208218 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.511099996307166e-05, "count": 1, "self": 4.511099996307166e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 348.0652949210498, "count": 311576, "is_parallel": true, "self": 7.311375475193017, "children": { "process_trajectory": { "total": 193.2930408948596, "count": 311576, "is_parallel": true, "self": 192.29040123285995, "children": { "RLTrainer._checkpoint": { "total": 1.0026396619996376, "count": 4, "is_parallel": true, "self": 1.0026396619996376 } } }, "_update_policy": { "total": 147.46087855099722, "count": 70, "is_parallel": true, "self": 56.242486161010675, "children": { "TorchPPOOptimizer.update": { "total": 91.21839238998655, "count": 3567, "is_parallel": true, "self": 91.21839238998655 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13340252099987993, "count": 1, "self": 0.0010547809997660806, "children": { "RLTrainer._checkpoint": { "total": 0.13234774000011384, "count": 1, "self": 0.13234774000011384 } } } } } } }