{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7092481255531311, "min": 0.6914249062538147, "max": 2.859597682952881, "count": 40 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7216.599609375, "min": 6670.17626953125, "max": 29253.68359375, "count": 40 }, "SnowballTarget.Step.mean": { "value": 399992.0, "min": 9952.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Step.sum": { "value": 399992.0, "min": 9952.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.60815143585205, "min": 0.5177081227302551, "max": 13.718135833740234, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2653.589599609375, "min": 100.43537139892578, "max": 2805.37451171875, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0768792116551755, "min": 0.06191642284279177, "max": 0.07718766891733085, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.307516846620702, "min": 0.25649684770706144, "max": 0.3731950204773788, "count": 40 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.203520383101468, "min": 0.126542127057773, "max": 0.2933554678570991, "count": 40 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.814081532405872, "min": 0.506168508231092, "max": 1.2733594412897147, "count": 40 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.891098702999994e-06, "min": 3.891098702999994e-06, "max": 0.000295941001353, "count": 40 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.5564394811999976e-05, "min": 1.5564394811999976e-05, "max": 0.0014425800191399996, "count": 40 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.101297, "min": 0.101297, "max": 0.19864700000000002, "count": 40 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.405188, "min": 0.405188, "max": 0.98086, "count": 40 }, "SnowballTarget.Policy.Beta.mean": { "value": 7.472029999999992e-05, "min": 7.472029999999992e-05, "max": 0.004932485299999999, "count": 40 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00029888119999999966, "min": 0.00029888119999999966, "max": 0.024044914, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.613636363636363, "min": 3.7954545454545454, "max": 26.954545454545453, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1171.0, "min": 167.0, "max": 1482.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.613636363636363, "min": 3.7954545454545454, "max": 26.954545454545453, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1171.0, "min": 167.0, "max": 1482.0, "count": 40 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680016092", "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": "1680017007" }, "total": 915.4806048120001, "count": 1, "self": 0.7804635680000729, "children": { "run_training.setup": { "total": 0.1130621949999977, "count": 1, "self": 0.1130621949999977 }, "TrainerController.start_learning": { "total": 914.5870790490001, "count": 1, "self": 1.0963760829977218, "children": { "TrainerController._reset_env": { "total": 10.177959025999996, "count": 1, "self": 10.177959025999996 }, "TrainerController.advance": { "total": 903.1029277260022, "count": 36414, "self": 0.5579183590085677, "children": { "env_step": { "total": 902.5450093669937, "count": 36414, "self": 653.1010794930276, "children": { "SubprocessEnvManager._take_step": { "total": 248.9254561209683, "count": 36414, "self": 3.8669713699611634, "children": { "TorchPolicy.evaluate": { "total": 245.05848475100714, "count": 36414, "self": 245.05848475100714 } } }, "workers": { "total": 0.5184737529978065, "count": 36414, "self": 0.0, "children": { "worker_root": { "total": 911.6279454920107, "count": 36414, "is_parallel": true, "self": 433.6956312819878, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006304095000018606, "count": 1, "is_parallel": true, "self": 0.0043291879999856064, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019749070000329993, "count": 10, "is_parallel": true, "self": 0.0019749070000329993 } } }, "UnityEnvironment.step": { "total": 0.08969511200001534, "count": 1, "is_parallel": true, "self": 0.0005922080000004826, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044667899999240035, "count": 1, "is_parallel": true, "self": 0.00044667899999240035 }, "communicator.exchange": { "total": 0.08681415600000264, "count": 1, "is_parallel": true, "self": 0.08681415600000264 }, "steps_from_proto": { "total": 0.0018420690000198192, "count": 1, "is_parallel": true, "self": 0.0003875090000065029, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014545600000133163, "count": 10, "is_parallel": true, "self": 0.0014545600000133163 } } } } } } }, "UnityEnvironment.step": { "total": 477.93231421002287, "count": 36413, "is_parallel": true, "self": 18.9226054440349, "children": { "UnityEnvironment._generate_step_input": { "total": 10.234040669987394, "count": 36413, "is_parallel": true, "self": 10.234040669987394 }, "communicator.exchange": { "total": 387.5469674680029, "count": 36413, "is_parallel": true, "self": 387.5469674680029 }, "steps_from_proto": { "total": 61.22870062799768, "count": 36413, "is_parallel": true, "self": 12.181203025999196, "children": { "_process_rank_one_or_two_observation": { "total": 49.04749760199849, "count": 364130, "is_parallel": true, "self": 49.04749760199849 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00022863499998493353, "count": 1, "self": 0.00022863499998493353, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 896.866285206891, "count": 766448, "is_parallel": true, "self": 18.411496065994015, "children": { "process_trajectory": { "total": 497.5298746208978, "count": 766448, "is_parallel": true, "self": 486.34885421489827, "children": { "RLTrainer._checkpoint": { "total": 11.181020405999504, "count": 40, "is_parallel": true, "self": 11.181020405999504 } } }, "_update_policy": { "total": 380.9249145199993, "count": 181, "is_parallel": true, "self": 146.5094337030053, "children": { "TorchPPOOptimizer.update": { "total": 234.41548081699398, "count": 9225, "is_parallel": true, "self": 234.41548081699398 } } } } } } } } }, "TrainerController._save_models": { "total": 0.20958757900007186, "count": 1, "self": 0.0013426230000277428, "children": { "RLTrainer._checkpoint": { "total": 0.2082449560000441, "count": 1, "self": 0.2082449560000441 } } } } } } }