{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8127557039260864, "min": 0.810983419418335, "max": 2.8731558322906494, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7760.19140625, "min": 7760.19140625, "max": 29423.98828125, "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": 13.055801391601562, "min": 0.26122593879699707, "max": 13.077880859375, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2545.88134765625, "min": 50.67782974243164, "max": 2667.8876953125, "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": 0.06433301769121659, "min": 0.0625133138284368, "max": 0.07504908876948962, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25733207076486636, "min": 0.256538518928174, "max": 0.3752454438474481, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19114929978169648, "min": 0.10991448852776861, "max": 0.3110489137470722, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7645971991267859, "min": 0.43965795411107444, "max": 1.385029620399662, "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": 25.863636363636363, "min": 2.977272727272727, "max": 25.863636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1138.0, "min": 131.0, "max": 1413.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.863636363636363, "min": 2.977272727272727, "max": 25.863636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1138.0, "min": 131.0, "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": "1674323017", "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": "1674323506" }, "total": 488.53702098199994, "count": 1, "self": 0.3953393150000011, "children": { "run_training.setup": { "total": 0.1115964680000161, "count": 1, "self": 0.1115964680000161 }, "TrainerController.start_learning": { "total": 488.0300851989999, "count": 1, "self": 0.6894928569820422, "children": { "TrainerController._reset_env": { "total": 9.932165766000026, "count": 1, "self": 9.932165766000026 }, "TrainerController.advance": { "total": 477.27202520501794, "count": 18201, "self": 0.3606337270346103, "children": { "env_step": { "total": 476.91139147798333, "count": 18201, "self": 313.4284189489831, "children": { "SubprocessEnvManager._take_step": { "total": 163.1445530619883, "count": 18201, "self": 1.7959171119982784, "children": { "TorchPolicy.evaluate": { "total": 161.34863594999, "count": 18201, "self": 37.58109736498591, "children": { "TorchPolicy.sample_actions": { "total": 123.7675385850041, "count": 18201, "self": 123.7675385850041 } } } } }, "workers": { "total": 0.3384194670119314, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 486.3592254169911, "count": 18201, "is_parallel": true, "self": 226.60297920400944, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0059990140000536485, "count": 1, "is_parallel": true, "self": 0.0035038109998595246, "children": { "_process_rank_one_or_two_observation": { "total": 0.002495203000194124, "count": 10, "is_parallel": true, "self": 0.002495203000194124 } } }, "UnityEnvironment.step": { "total": 0.03698322499997175, "count": 1, "is_parallel": true, "self": 0.00035926299995026056, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033937900002456445, "count": 1, "is_parallel": true, "self": 0.00033937900002456445 }, "communicator.exchange": { "total": 0.03445413899999039, "count": 1, "is_parallel": true, "self": 0.03445413899999039 }, "steps_from_proto": { "total": 0.001830444000006537, "count": 1, "is_parallel": true, "self": 0.0004557790001626927, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013746649998438443, "count": 10, "is_parallel": true, "self": 0.0013746649998438443 } } } } } } }, "UnityEnvironment.step": { "total": 259.75624621298164, "count": 18200, "is_parallel": true, "self": 9.69179004697105, "children": { "UnityEnvironment._generate_step_input": { "total": 5.761454752990062, "count": 18200, "is_parallel": true, "self": 5.761454752990062 }, "communicator.exchange": { "total": 206.56625469300081, "count": 18200, "is_parallel": true, "self": 206.56625469300081 }, "steps_from_proto": { "total": 37.73674672001971, "count": 18200, "is_parallel": true, "self": 8.180710088004844, "children": { "_process_rank_one_or_two_observation": { "total": 29.556036632014866, "count": 182000, "is_parallel": true, "self": 29.556036632014866 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.936999994242797e-05, "count": 1, "self": 4.936999994242797e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 473.6166840919137, "count": 425787, "is_parallel": true, "self": 11.76156093883742, "children": { "process_trajectory": { "total": 277.06716441707556, "count": 425787, "is_parallel": true, "self": 276.31926125207576, "children": { "RLTrainer._checkpoint": { "total": 0.7479031649997978, "count": 4, "is_parallel": true, "self": 0.7479031649997978 } } }, "_update_policy": { "total": 184.78795873600075, "count": 90, "is_parallel": true, "self": 43.0425393450048, "children": { "TorchPPOOptimizer.update": { "total": 141.74541939099595, "count": 4587, "is_parallel": true, "self": 141.74541939099595 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13635200099997746, "count": 1, "self": 0.0009308799999416806, "children": { "RLTrainer._checkpoint": { "total": 0.13542112100003578, "count": 1, "self": 0.13542112100003578 } } } } } } }