{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9906118512153625, "min": 0.9537782073020935, "max": 2.856226921081543, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9556.4326171875, "min": 9556.4326171875, "max": 29250.62109375, "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": 13.039422035217285, "min": 0.3735616207122803, "max": 13.094487190246582, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2542.687255859375, "min": 72.47095489501953, "max": 2671.275390625, "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": 0.06828593485689077, "min": 0.060268536406082984, "max": 0.07711215339612168, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2731437394275631, "min": 0.24107414562433194, "max": 0.3713174966967427, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2561562522223183, "min": 0.1284158771136301, "max": 0.28267765235082776, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.0246250088892732, "min": 0.5136635084545204, "max": 1.3695294062296548, "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": 25.318181818181817, "min": 3.5454545454545454, "max": 26.068181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1114.0, "min": 156.0, "max": 1418.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.318181818181817, "min": 3.5454545454545454, "max": 26.068181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1114.0, "min": 156.0, "max": 1418.0, "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": "1677593339", "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": "1.22.4", "end_time_seconds": "1677593809" }, "total": 470.75704731200005, "count": 1, "self": 0.6847691479999867, "children": { "run_training.setup": { "total": 0.11282435700002225, "count": 1, "self": 0.11282435700002225 }, "TrainerController.start_learning": { "total": 469.95945380700005, "count": 1, "self": 0.5701179510147085, "children": { "TrainerController._reset_env": { "total": 10.827724839999973, "count": 1, "self": 10.827724839999973 }, "TrainerController.advance": { "total": 458.36654292798517, "count": 18220, "self": 0.30436803097916254, "children": { "env_step": { "total": 458.062174897006, "count": 18220, "self": 315.33247069798506, "children": { "SubprocessEnvManager._take_step": { "total": 142.44592060300727, "count": 18220, "self": 1.7452979430080404, "children": { "TorchPolicy.evaluate": { "total": 140.70062265999923, "count": 18220, "self": 31.679460216003122, "children": { "TorchPolicy.sample_actions": { "total": 109.0211624439961, "count": 18220, "self": 109.0211624439961 } } } } }, "workers": { "total": 0.2837835960136772, "count": 18220, "self": 0.0, "children": { "worker_root": { "total": 468.36291684598984, "count": 18220, "is_parallel": true, "self": 227.8438493310066, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.009674763000020903, "count": 1, "is_parallel": true, "self": 0.00441263900006561, "children": { "_process_rank_one_or_two_observation": { "total": 0.005262123999955293, "count": 10, "is_parallel": true, "self": 0.005262123999955293 } } }, "UnityEnvironment.step": { "total": 0.04786006799997722, "count": 1, "is_parallel": true, "self": 0.0006127149999883841, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00029099799996856746, "count": 1, "is_parallel": true, "self": 0.00029099799996856746 }, "communicator.exchange": { "total": 0.04505204600002344, "count": 1, "is_parallel": true, "self": 0.04505204600002344 }, "steps_from_proto": { "total": 0.0019043089999968288, "count": 1, "is_parallel": true, "self": 0.0004405769999493714, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014637320000474574, "count": 10, "is_parallel": true, "self": 0.0014637320000474574 } } } } } } }, "UnityEnvironment.step": { "total": 240.51906751498325, "count": 18219, "is_parallel": true, "self": 9.826744476981048, "children": { "UnityEnvironment._generate_step_input": { "total": 5.34811512499607, "count": 18219, "is_parallel": true, "self": 5.34811512499607 }, "communicator.exchange": { "total": 193.60393186600618, "count": 18219, "is_parallel": true, "self": 193.60393186600618 }, "steps_from_proto": { "total": 31.740276046999952, "count": 18219, "is_parallel": true, "self": 6.9055468439820515, "children": { "_process_rank_one_or_two_observation": { "total": 24.8347292030179, "count": 182190, "is_parallel": true, "self": 24.8347292030179 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00018371800001659722, "count": 1, "self": 0.00018371800001659722, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 454.9878973029603, "count": 396384, "is_parallel": true, "self": 9.94598038202264, "children": { "process_trajectory": { "total": 259.6085108589376, "count": 396384, "is_parallel": true, "self": 258.6436893549376, "children": { "RLTrainer._checkpoint": { "total": 0.9648215040000423, "count": 4, "is_parallel": true, "self": 0.9648215040000423 } } }, "_update_policy": { "total": 185.43340606200002, "count": 90, "is_parallel": true, "self": 64.6556427959963, "children": { "TorchPPOOptimizer.update": { "total": 120.77776326600372, "count": 4587, "is_parallel": true, "self": 120.77776326600372 } } } } } } } } }, "TrainerController._save_models": { "total": 0.19488437000018166, "count": 1, "self": 0.001176084000235278, "children": { "RLTrainer._checkpoint": { "total": 0.19370828599994638, "count": 1, "self": 0.19370828599994638 } } } } } } }