{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9950110912322998, "min": 0.9858764410018921, "max": 2.863276958465576, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9598.8720703125, "min": 9598.8720703125, "max": 29291.32421875, "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": 12.569748878479004, "min": 0.3102013170719147, "max": 12.569748878479004, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2451.10107421875, "min": 60.179054260253906, "max": 2548.483154296875, "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": 0.07284445620202096, "min": 0.061468905737445526, "max": 0.07387532094635033, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29137782480808383, "min": 0.25822726774198346, "max": 0.36937660473175166, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21853815396783025, "min": 0.1150600623850729, "max": 0.27857475011956456, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.874152615871321, "min": 0.4602402495402916, "max": 1.3415659642687028, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.130097290000004e-06, "min": 8.130097290000004e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.2520389160000015e-05, "min": 3.2520389160000015e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10271, "min": 0.10271, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41084, "min": 0.41084, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00014522900000000006, "min": 0.00014522900000000006, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005809160000000002, "min": 0.0005809160000000002, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.681818181818183, "min": 2.977272727272727, "max": 25.113636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1086.0, "min": 131.0, "max": 1348.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.681818181818183, "min": 2.977272727272727, "max": 25.113636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1086.0, "min": 131.0, "max": 1348.0, "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": "1691836934", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "1691837417" }, "total": 482.41953630999996, "count": 1, "self": 0.7475997610000036, "children": { "run_training.setup": { "total": 0.04356187199999795, "count": 1, "self": 0.04356187199999795 }, "TrainerController.start_learning": { "total": 481.62837467699995, "count": 1, "self": 0.5500197040072408, "children": { "TrainerController._reset_env": { "total": 5.411737351999989, "count": 1, "self": 5.411737351999989 }, "TrainerController.advance": { "total": 475.4425134909927, "count": 18220, "self": 0.2574203859988984, "children": { "env_step": { "total": 475.1850931049938, "count": 18220, "self": 346.5190435499991, "children": { "SubprocessEnvManager._take_step": { "total": 128.39553708198991, "count": 18220, "self": 1.7882255189890657, "children": { "TorchPolicy.evaluate": { "total": 126.60731156300085, "count": 18220, "self": 126.60731156300085 } } }, "workers": { "total": 0.2705124730048283, "count": 18220, "self": 0.0, "children": { "worker_root": { "total": 479.75187572700025, "count": 18220, "is_parallel": true, "self": 226.13953530299813, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005545012000027327, "count": 1, "is_parallel": true, "self": 0.0040783379999993485, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014666740000279788, "count": 10, "is_parallel": true, "self": 0.0014666740000279788 } } }, "UnityEnvironment.step": { "total": 0.07703151900000194, "count": 1, "is_parallel": true, "self": 0.0010450610000134475, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004691699999739285, "count": 1, "is_parallel": true, "self": 0.0004691699999739285 }, "communicator.exchange": { "total": 0.07067505399993479, "count": 1, "is_parallel": true, "self": 0.07067505399993479 }, "steps_from_proto": { "total": 0.00484223400007977, "count": 1, "is_parallel": true, "self": 0.0011765540000396868, "children": { "_process_rank_one_or_two_observation": { "total": 0.0036656800000400835, "count": 10, "is_parallel": true, "self": 0.0036656800000400835 } } } } } } }, "UnityEnvironment.step": { "total": 253.61234042400213, "count": 18219, "is_parallel": true, "self": 10.669674150993842, "children": { "UnityEnvironment._generate_step_input": { "total": 5.338565145006214, "count": 18219, "is_parallel": true, "self": 5.338565145006214 }, "communicator.exchange": { "total": 201.09473877300138, "count": 18219, "is_parallel": true, "self": 201.09473877300138 }, "steps_from_proto": { "total": 36.50936235500069, "count": 18219, "is_parallel": true, "self": 6.635759962021666, "children": { "_process_rank_one_or_two_observation": { "total": 29.873602392979024, "count": 182190, "is_parallel": true, "self": 29.873602392979024 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001436999999668842, "count": 1, "self": 0.0001436999999668842, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 471.58694855698263, "count": 452319, "is_parallel": true, "self": 10.341350821013066, "children": { "process_trajectory": { "total": 259.0511954089691, "count": 452319, "is_parallel": true, "self": 257.953184873969, "children": { "RLTrainer._checkpoint": { "total": 1.0980105350000713, "count": 4, "is_parallel": true, "self": 1.0980105350000713 } } }, "_update_policy": { "total": 202.1944023270005, "count": 90, "is_parallel": true, "self": 80.51881307099973, "children": { "TorchPPOOptimizer.update": { "total": 121.67558925600076, "count": 4587, "is_parallel": true, "self": 121.67558925600076 } } } } } } } } }, "TrainerController._save_models": { "total": 0.22396043000003374, "count": 1, "self": 0.0011140120000163733, "children": { "RLTrainer._checkpoint": { "total": 0.22284641800001737, "count": 1, "self": 0.22284641800001737 } } } } } } }