{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9331536293029785, "min": 0.9331536293029785, "max": 2.8651230335235596, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8909.7509765625, "min": 8909.7509765625, "max": 29593.85546875, "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": 11.842415809631348, "min": 0.5176137089729309, "max": 11.863922119140625, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2309.27099609375, "min": 100.41706085205078, "max": 2409.17138671875, "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": 0.06211310921849765, "min": 0.061827638707530004, "max": 0.07309658595398764, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2484524368739906, "min": 0.24731055483012002, "max": 0.3487019154366434, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19468995147183832, "min": 0.12456476411042625, "max": 0.2873734997183669, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7787598058873533, "min": 0.498259056441705, "max": 1.4368674985918344, "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": 23.522727272727273, "min": 3.5681818181818183, "max": 23.522727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1035.0, "min": 157.0, "max": 1292.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.522727272727273, "min": 3.5681818181818183, "max": 23.522727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1035.0, "min": 157.0, "max": 1292.0, "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": "1675931004", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1675931450" }, "total": 446.452020036, "count": 1, "self": 0.43573054700010516, "children": { "run_training.setup": { "total": 0.10808811699996568, "count": 1, "self": 0.10808811699996568 }, "TrainerController.start_learning": { "total": 445.90820137199995, "count": 1, "self": 0.4940908320036783, "children": { "TrainerController._reset_env": { "total": 9.587460676000035, "count": 1, "self": 9.587460676000035 }, "TrainerController.advance": { "total": 435.69146132699626, "count": 18204, "self": 0.2571603709924375, "children": { "env_step": { "total": 435.4343009560038, "count": 18204, "self": 299.2967226590085, "children": { "SubprocessEnvManager._take_step": { "total": 135.88457513299915, "count": 18204, "self": 1.4416172229960011, "children": { "TorchPolicy.evaluate": { "total": 134.44295791000314, "count": 18204, "self": 29.48482800700782, "children": { "TorchPolicy.sample_actions": { "total": 104.95812990299532, "count": 18204, "self": 104.95812990299532 } } } } }, "workers": { "total": 0.2530031639961976, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 444.5116216209908, "count": 18204, "is_parallel": true, "self": 217.61963473399777, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0062016390000394495, "count": 1, "is_parallel": true, "self": 0.0035828959999548715, "children": { "_process_rank_one_or_two_observation": { "total": 0.002618743000084578, "count": 10, "is_parallel": true, "self": 0.002618743000084578 } } }, "UnityEnvironment.step": { "total": 0.03310804399995959, "count": 1, "is_parallel": true, "self": 0.00043733699993708797, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040476100002706517, "count": 1, "is_parallel": true, "self": 0.00040476100002706517 }, "communicator.exchange": { "total": 0.030193215999986478, "count": 1, "is_parallel": true, "self": 0.030193215999986478 }, "steps_from_proto": { "total": 0.00207273000000896, "count": 1, "is_parallel": true, "self": 0.0005968140000049971, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014759160000039628, "count": 10, "is_parallel": true, "self": 0.0014759160000039628 } } } } } } }, "UnityEnvironment.step": { "total": 226.89198688699304, "count": 18203, "is_parallel": true, "self": 9.351901399000496, "children": { "UnityEnvironment._generate_step_input": { "total": 5.1354868539932, "count": 18203, "is_parallel": true, "self": 5.1354868539932 }, "communicator.exchange": { "total": 181.92490675899063, "count": 18203, "is_parallel": true, "self": 181.92490675899063 }, "steps_from_proto": { "total": 30.47969187500871, "count": 18203, "is_parallel": true, "self": 6.496801942023183, "children": { "_process_rank_one_or_two_observation": { "total": 23.98288993298553, "count": 182030, "is_parallel": true, "self": 23.98288993298553 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011782399997173343, "count": 1, "self": 0.00011782399997173343, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 432.30496129994964, "count": 393149, "is_parallel": true, "self": 9.767086179986052, "children": { "process_trajectory": { "total": 248.959623694963, "count": 393149, "is_parallel": true, "self": 248.18861743796316, "children": { "RLTrainer._checkpoint": { "total": 0.7710062569998399, "count": 4, "is_parallel": true, "self": 0.7710062569998399 } } }, "_update_policy": { "total": 173.5782514250006, "count": 90, "is_parallel": true, "self": 60.35259960300277, "children": { "TorchPPOOptimizer.update": { "total": 113.22565182199781, "count": 4587, "is_parallel": true, "self": 113.22565182199781 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13507071300000462, "count": 1, "self": 0.0009305209999865838, "children": { "RLTrainer._checkpoint": { "total": 0.13414019200001803, "count": 1, "self": 0.13414019200001803 } } } } } } }