{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.770317554473877, "min": 0.770317554473877, "max": 2.8666982650756836, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7388.8857421875, "min": 7388.8857421875, "max": 29389.390625, "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": 12.99460220336914, "min": 0.42120277881622314, "max": 12.99460220336914, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2533.947509765625, "min": 81.71334075927734, "max": 2639.5771484375, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06353202588783746, "min": 0.061540891262919506, "max": 0.0758252798613445, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25412810355134985, "min": 0.25412810355134985, "max": 0.37912639930672254, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2083206359370082, "min": 0.12831390665172984, "max": 0.282460212356904, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8332825437480328, "min": 0.5132556266069194, "max": 1.41230106178452, "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": 25.772727272727273, "min": 3.340909090909091, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1134.0, "min": 147.0, "max": 1413.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.772727272727273, "min": 3.340909090909091, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1134.0, "min": 147.0, "max": 1413.0, "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": "1679488379", "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": "1679488827" }, "total": 447.9371319659999, "count": 1, "self": 0.43176150100009636, "children": { "run_training.setup": { "total": 0.16503923899995243, "count": 1, "self": 0.16503923899995243 }, "TrainerController.start_learning": { "total": 447.3403312259999, "count": 1, "self": 0.47468783801753034, "children": { "TrainerController._reset_env": { "total": 8.435412219, "count": 1, "self": 8.435412219 }, "TrainerController.advance": { "total": 438.24838037898235, "count": 18225, "self": 0.24876220298654061, "children": { "env_step": { "total": 437.9996181759958, "count": 18225, "self": 315.8553467040282, "children": { "SubprocessEnvManager._take_step": { "total": 121.89867156499236, "count": 18225, "self": 2.3686666109946373, "children": { "TorchPolicy.evaluate": { "total": 119.53000495399772, "count": 18225, "self": 119.53000495399772 } } }, "workers": { "total": 0.2455999069752579, "count": 18225, "self": 0.0, "children": { "worker_root": { "total": 446.02025612100886, "count": 18225, "is_parallel": true, "self": 215.0911838339931, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006230085000083818, "count": 1, "is_parallel": true, "self": 0.00393140200014841, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022986829999354086, "count": 10, "is_parallel": true, "self": 0.0022986829999354086 } } }, "UnityEnvironment.step": { "total": 0.034214014999975007, "count": 1, "is_parallel": true, "self": 0.00041271599991432595, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003367900000057489, "count": 1, "is_parallel": true, "self": 0.0003367900000057489 }, "communicator.exchange": { "total": 0.031901464000043234, "count": 1, "is_parallel": true, "self": 0.031901464000043234 }, "steps_from_proto": { "total": 0.001563045000011698, "count": 1, "is_parallel": true, "self": 0.00035982899987629935, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012032160001353986, "count": 10, "is_parallel": true, "self": 0.0012032160001353986 } } } } } } }, "UnityEnvironment.step": { "total": 230.92907228701574, "count": 18224, "is_parallel": true, "self": 9.322426464010391, "children": { "UnityEnvironment._generate_step_input": { "total": 5.068600924993234, "count": 18224, "is_parallel": true, "self": 5.068600924993234 }, "communicator.exchange": { "total": 186.56592391001425, "count": 18224, "is_parallel": true, "self": 186.56592391001425 }, "steps_from_proto": { "total": 29.97212098799787, "count": 18224, "is_parallel": true, "self": 5.781107087993405, "children": { "_process_rank_one_or_two_observation": { "total": 24.191013900004464, "count": 182240, "is_parallel": true, "self": 24.191013900004464 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00010602699990158726, "count": 1, "self": 0.00010602699990158726, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 435.03353908600957, "count": 388528, "is_parallel": true, "self": 9.493187813967893, "children": { "process_trajectory": { "total": 241.01637122004206, "count": 388528, "is_parallel": true, "self": 239.21329560504205, "children": { "RLTrainer._checkpoint": { "total": 1.8030756150000116, "count": 4, "is_parallel": true, "self": 1.8030756150000116 } } }, "_update_policy": { "total": 184.52398005199962, "count": 90, "is_parallel": true, "self": 68.52147736800225, "children": { "TorchPPOOptimizer.update": { "total": 116.00250268399736, "count": 4584, "is_parallel": true, "self": 116.00250268399736 } } } } } } } } }, "TrainerController._save_models": { "total": 0.181744763000097, "count": 1, "self": 0.0008792880000783043, "children": { "RLTrainer._checkpoint": { "total": 0.1808654750000187, "count": 1, "self": 0.1808654750000187 } } } } } } }