{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9962714910507202, "min": 0.9925804734230042, "max": 2.8734798431396484, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9523.359375, "min": 9523.359375, "max": 29427.306640625, "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": 12.39413070678711, "min": 0.3540612459182739, "max": 12.39413070678711, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2416.85546875, "min": 68.68788146972656, "max": 2506.9775390625, "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": 0.0708833147517747, "min": 0.0636396039697894, "max": 0.07690932188137702, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2835332590070988, "min": 0.2545584158791576, "max": 0.3727140250255116, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21426570795330346, "min": 0.10564942475563537, "max": 0.2781321480139798, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8570628318132139, "min": 0.42259769902254146, "max": 1.3281569895791074, "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": 24.477272727272727, "min": 3.0, "max": 24.84090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1077.0, "min": 132.0, "max": 1346.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.477272727272727, "min": 3.0, "max": 24.84090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1077.0, "min": 132.0, "max": 1346.0, "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": "1682333754", "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": "1682334272" }, "total": 517.593229244, "count": 1, "self": 0.43673161099991376, "children": { "run_training.setup": { "total": 0.11742357200000697, "count": 1, "self": 0.11742357200000697 }, "TrainerController.start_learning": { "total": 517.0390740610001, "count": 1, "self": 0.6729901719972986, "children": { "TrainerController._reset_env": { "total": 3.9381822080000575, "count": 1, "self": 3.9381822080000575 }, "TrainerController.advance": { "total": 512.2779868930028, "count": 18202, "self": 0.32722357500665566, "children": { "env_step": { "total": 511.9507633179961, "count": 18202, "self": 372.35081873100205, "children": { "SubprocessEnvManager._take_step": { "total": 139.2682114689885, "count": 18202, "self": 2.0435826539790014, "children": { "TorchPolicy.evaluate": { "total": 137.2246288150095, "count": 18202, "self": 137.2246288150095 } } }, "workers": { "total": 0.33173311800555894, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 515.3251687269897, "count": 18202, "is_parallel": true, "self": 237.32603900099275, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005740896000020257, "count": 1, "is_parallel": true, "self": 0.004075656000168237, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016652399998520195, "count": 10, "is_parallel": true, "self": 0.0016652399998520195 } } }, "UnityEnvironment.step": { "total": 0.04053574200008825, "count": 1, "is_parallel": true, "self": 0.001722804999985783, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040623300003517215, "count": 1, "is_parallel": true, "self": 0.00040623300003517215 }, "communicator.exchange": { "total": 0.03618575200005125, "count": 1, "is_parallel": true, "self": 0.03618575200005125 }, "steps_from_proto": { "total": 0.002220952000016041, "count": 1, "is_parallel": true, "self": 0.0004454769999711061, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017754750000449349, "count": 10, "is_parallel": true, "self": 0.0017754750000449349 } } } } } } }, "UnityEnvironment.step": { "total": 277.9991297259969, "count": 18201, "is_parallel": true, "self": 10.972412975987254, "children": { "UnityEnvironment._generate_step_input": { "total": 6.284306320010501, "count": 18201, "is_parallel": true, "self": 6.284306320010501 }, "communicator.exchange": { "total": 223.38351054300335, "count": 18201, "is_parallel": true, "self": 223.38351054300335 }, "steps_from_proto": { "total": 37.3588998869958, "count": 18201, "is_parallel": true, "self": 7.601957493990426, "children": { "_process_rank_one_or_two_observation": { "total": 29.756942393005374, "count": 182010, "is_parallel": true, "self": 29.756942393005374 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015680599994993827, "count": 1, "self": 0.00015680599994993827, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 508.08423322002704, "count": 453313, "is_parallel": true, "self": 11.875213977108046, "children": { "process_trajectory": { "total": 282.64630846591865, "count": 453313, "is_parallel": true, "self": 281.4695462969187, "children": { "RLTrainer._checkpoint": { "total": 1.1767621689999714, "count": 4, "is_parallel": true, "self": 1.1767621689999714 } } }, "_update_policy": { "total": 213.56271077700035, "count": 90, "is_parallel": true, "self": 74.49600602501164, "children": { "TorchPPOOptimizer.update": { "total": 139.0667047519887, "count": 4587, "is_parallel": true, "self": 139.0667047519887 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1497579819999828, "count": 1, "self": 0.0010194919998411933, "children": { "RLTrainer._checkpoint": { "total": 0.1487384900001416, "count": 1, "self": 0.1487384900001416 } } } } } } }