{ "name": "root", "gauges": { "Worm.Policy.Entropy.mean": { "value": 0.4339846968650818, "min": 0.4339846968650818, "max": 1.425347089767456, "count": 233 }, "Worm.Policy.Entropy.sum": { "value": 13019.541015625, "min": 13019.541015625, "max": 42760.4140625, "count": 233 }, "Worm.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 233 }, "Worm.Environment.EpisodeLength.sum": { "value": 29970.0, "min": 29970.0, "max": 29970.0, "count": 233 }, "Worm.Step.mean": { "value": 6989000.0, "min": 29000.0, "max": 6989000.0, "count": 233 }, "Worm.Step.sum": { "value": 6989000.0, "min": 29000.0, "max": 6989000.0, "count": 233 }, "Worm.Policy.ExtrinsicValueEstimate.mean": { "value": 255.49131774902344, "min": 0.05548596382141113, "max": 256.8880310058594, "count": 233 }, "Worm.Policy.ExtrinsicValueEstimate.sum": { "value": 7664.73974609375, "min": 1.664578914642334, "max": 7706.640625, "count": 233 }, "Worm.Environment.CumulativeReward.mean": { "value": 1280.3476847330728, "min": 0.3973975207271247, "max": 1294.5965779622395, "count": 233 }, "Worm.Environment.CumulativeReward.sum": { "value": 38410.43054199219, "min": 11.524528101086617, "max": 38837.89733886719, "count": 233 }, "Worm.Policy.ExtrinsicReward.mean": { "value": 1280.3476847330728, "min": 0.3973975207271247, "max": 1294.5965779622395, "count": 233 }, "Worm.Policy.ExtrinsicReward.sum": { "value": 38410.43054199219, "min": 11.524528101086617, "max": 38837.89733886719, "count": 233 }, "Worm.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 233 }, "Worm.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 233 }, "Worm.Losses.PolicyLoss.mean": { "value": 0.016954120023209337, "min": 0.014543257566609619, "max": 0.02564329657678692, "count": 232 }, "Worm.Losses.PolicyLoss.sum": { "value": 0.016954120023209337, "min": 0.014543257566609619, "max": 0.02564329657678692, "count": 232 }, "Worm.Losses.ValueLoss.mean": { "value": 46.91152316502163, "min": 0.0017147937673144043, "max": 52.668317140851705, "count": 232 }, "Worm.Losses.ValueLoss.sum": { "value": 46.91152316502163, "min": 0.0017147937673144043, "max": 52.668317140851705, "count": 232 }, "Worm.Policy.LearningRate.mean": { "value": 1.7143851428571304e-06, "min": 1.7143851428571304e-06, "max": 0.00029871428614285713, "count": 232 }, "Worm.Policy.LearningRate.sum": { "value": 1.7143851428571304e-06, "min": 1.7143851428571304e-06, "max": 0.00029871428614285713, "count": 232 }, "Worm.Policy.Epsilon.mean": { "value": 0.10057142857142856, "min": 0.10057142857142856, "max": 0.19957142857142848, "count": 232 }, "Worm.Policy.Epsilon.sum": { "value": 0.10057142857142856, "min": 0.10057142857142856, "max": 0.19957142857142848, "count": 232 }, "Worm.Policy.Beta.mean": { "value": 3.851428571428551e-05, "min": 3.851428571428551e-05, "max": 0.004978614285714285, "count": 232 }, "Worm.Policy.Beta.sum": { "value": 3.851428571428551e-05, "min": 3.851428571428551e-05, "max": 0.004978614285714285, "count": 232 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1660212893", "python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Worm.yaml --env=./trained-envs-executables/linux/Worm/Worm --run-id=Worm2 Training --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": "1660224916" }, "total": 12022.860046743, "count": 1, "self": 0.5516019420028897, "children": { "run_training.setup": { "total": 0.06923555699995632, "count": 1, "self": 0.06923555699995632 }, "TrainerController.start_learning": { "total": 12022.239209243999, "count": 1, "self": 17.006347716003802, "children": { "TrainerController._reset_env": { "total": 12.363578319999988, "count": 1, "self": 12.363578319999988 }, "TrainerController.advance": { "total": 11992.463333555996, "count": 701000, "self": 18.919621536715567, "children": { "env_step": { "total": 8936.103971909284, "count": 701000, "self": 7595.906745481266, "children": { "SubprocessEnvManager._take_step": { "total": 1330.24418947316, "count": 701000, "self": 78.1668792699611, "children": { "TorchPolicy.evaluate": { "total": 1252.077310203199, "count": 701000, "self": 304.6395322953017, "children": { "TorchPolicy.sample_actions": { "total": 947.4377779078973, "count": 701000, "self": 947.4377779078973 } } } } }, "workers": { "total": 9.95303695485859, "count": 701000, "self": 0.0, "children": { "worker_root": { "total": 11989.978133554368, "count": 701000, "is_parallel": true, "self": 5483.934479929755, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012625439999283117, "count": 1, "is_parallel": true, "self": 0.0004167579998011206, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008457860001271911, "count": 2, "is_parallel": true, "self": 0.0008457860001271911 } } }, "UnityEnvironment.step": { "total": 0.04086264500006109, "count": 1, "is_parallel": true, "self": 0.0003425719999086141, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005374710001433414, "count": 1, "is_parallel": true, "self": 0.0005374710001433414 }, "communicator.exchange": { "total": 0.03903397700014466, "count": 1, "is_parallel": true, "self": 0.03903397700014466 }, "steps_from_proto": { "total": 0.000948624999864478, "count": 1, "is_parallel": true, "self": 0.0003397880000193254, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006088369998451526, "count": 2, "is_parallel": true, "self": 0.0006088369998451526 } } } } } } }, "UnityEnvironment.step": { "total": 6506.043653624613, "count": 700999, "is_parallel": true, "self": 160.86337100917444, "children": { "UnityEnvironment._generate_step_input": { "total": 299.88446902831856, "count": 700999, "is_parallel": true, "self": 299.88446902831856 }, "communicator.exchange": { "total": 5615.445410939148, "count": 700999, "is_parallel": true, "self": 5615.445410939148 }, "steps_from_proto": { "total": 429.85040264797226, "count": 700999, "is_parallel": true, "self": 190.38673972843094, "children": { "_process_rank_one_or_two_observation": { "total": 239.46366291954132, "count": 1401998, "is_parallel": true, "self": 239.46366291954132 } } } } } } } } } } }, "trainer_advance": { "total": 3037.439740109996, "count": 701000, "self": 20.913014486292013, "children": { "process_trajectory": { "total": 589.7322016627002, "count": 701000, "self": 584.5715786516978, "children": { "RLTrainer._checkpoint": { "total": 5.160623011002372, "count": 14, "self": 5.160623011002372 } } }, "_update_policy": { "total": 2426.7945239610035, "count": 233, "self": 2035.6206693850027, "children": { "TorchPPOOptimizer.update": { "total": 391.17385457600085, "count": 16310, "self": 391.17385457600085 } } } } } } }, "trainer_threads": { "total": 1.700998836895451e-06, "count": 1, "self": 1.700998836895451e-06 }, "TrainerController._save_models": { "total": 0.40594795099968906, "count": 1, "self": 0.022390504998838878, "children": { "RLTrainer._checkpoint": { "total": 0.3835574460008502, "count": 1, "self": 0.3835574460008502 } } } } } } }