{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0145184993743896, "min": 1.0145184993743896, "max": 2.8714847564697266, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9708.9423828125, "min": 9708.9423828125, "max": 29470.046875, "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": 12.669929504394531, "min": 0.10942478477954865, "max": 12.669929504394531, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2470.63623046875, "min": 21.228408813476562, "max": 2556.941162109375, "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": 0.07248494698875468, "min": 0.06355403852962897, "max": 0.07626777024318775, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28993978795501874, "min": 0.2542161541185159, "max": 0.38133885121593875, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2089477636504407, "min": 0.10539230570201671, "max": 0.28455622976317124, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8357910546017628, "min": 0.42156922280806686, "max": 1.399077856365372, "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": 25.113636363636363, "min": 2.6363636363636362, "max": 25.113636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1105.0, "min": 116.0, "max": 1362.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.113636363636363, "min": 2.6363636363636362, "max": 25.113636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1105.0, "min": 116.0, "max": 1362.0, "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": "1690452939", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1690453444" }, "total": 504.87492837900004, "count": 1, "self": 0.4366930159999356, "children": { "run_training.setup": { "total": 0.03698476900001424, "count": 1, "self": 0.03698476900001424 }, "TrainerController.start_learning": { "total": 504.4012505940001, "count": 1, "self": 0.6344935689922977, "children": { "TrainerController._reset_env": { "total": 6.5381322370000134, "count": 1, "self": 6.5381322370000134 }, "TrainerController.advance": { "total": 497.07482755900776, "count": 18203, "self": 0.3173371780129628, "children": { "env_step": { "total": 496.7574903809948, "count": 18203, "self": 362.6190794599927, "children": { "SubprocessEnvManager._take_step": { "total": 133.81081788000813, "count": 18203, "self": 1.9142801819892838, "children": { "TorchPolicy.evaluate": { "total": 131.89653769801885, "count": 18203, "self": 131.89653769801885 } } }, "workers": { "total": 0.3275930409939747, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 502.71988773300063, "count": 18203, "is_parallel": true, "self": 234.06349244000546, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005752723000000515, "count": 1, "is_parallel": true, "self": 0.004307499999868014, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014452230001325006, "count": 10, "is_parallel": true, "self": 0.0014452230001325006 } } }, "UnityEnvironment.step": { "total": 0.03908623400002398, "count": 1, "is_parallel": true, "self": 0.0006388110000443703, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002762369999800285, "count": 1, "is_parallel": true, "self": 0.0002762369999800285 }, "communicator.exchange": { "total": 0.03592834899995978, "count": 1, "is_parallel": true, "self": 0.03592834899995978 }, "steps_from_proto": { "total": 0.002242837000039799, "count": 1, "is_parallel": true, "self": 0.0005593770001723897, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016834599998674094, "count": 10, "is_parallel": true, "self": 0.0016834599998674094 } } } } } } }, "UnityEnvironment.step": { "total": 268.65639529299517, "count": 18202, "is_parallel": true, "self": 11.222535126992739, "children": { "UnityEnvironment._generate_step_input": { "total": 5.78029513699687, "count": 18202, "is_parallel": true, "self": 5.78029513699687 }, "communicator.exchange": { "total": 214.3523623739958, "count": 18202, "is_parallel": true, "self": 214.3523623739958 }, "steps_from_proto": { "total": 37.301202655009774, "count": 18202, "is_parallel": true, "self": 7.160780249975005, "children": { "_process_rank_one_or_two_observation": { "total": 30.14042240503477, "count": 182020, "is_parallel": true, "self": 30.14042240503477 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012014399999316083, "count": 1, "self": 0.00012014399999316083, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 493.3348548230439, "count": 455591, "is_parallel": true, "self": 10.283144407119607, "children": { "process_trajectory": { "total": 270.6585116689241, "count": 455591, "is_parallel": true, "self": 269.8349197889239, "children": { "RLTrainer._checkpoint": { "total": 0.8235918800002082, "count": 4, "is_parallel": true, "self": 0.8235918800002082 } } }, "_update_policy": { "total": 212.39319874700016, "count": 90, "is_parallel": true, "self": 81.49802703500768, "children": { "TorchPPOOptimizer.update": { "total": 130.89517171199248, "count": 4587, "is_parallel": true, "self": 130.89517171199248 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15367708500002664, "count": 1, "self": 0.0008863739999469544, "children": { "RLTrainer._checkpoint": { "total": 0.15279071100007968, "count": 1, "self": 0.15279071100007968 } } } } } } }