{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7485129237174988, "min": 0.7459189295768738, "max": 2.8562512397766113, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7113.86669921875, "min": 7113.86669921875, "max": 27580.619140625, "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": 12.931973457336426, "min": 0.36002692580223083, "max": 12.931973457336426, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2521.73486328125, "min": 34.20255661010742, "max": 2629.231201171875, "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": 4378.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07143005984064932, "min": 0.0634824107939779, "max": 0.07450440518886728, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2857202393625973, "min": 0.1480563891693201, "max": 0.37252202594433637, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18356743458585412, "min": 0.11577610888372303, "max": 0.29279502110154015, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7342697383434165, "min": 0.23155221776744606, "max": 1.4639751055077008, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.0260976579999984e-06, "min": 7.0260976579999984e-06, "max": 0.000287526004158, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.8104390631999994e-05, "min": 2.8104390631999994e-05, "max": 0.0013138800620399998, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10234199999999999, "min": 0.10234199999999999, "max": 0.19584200000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40936799999999995, "min": 0.39168400000000003, "max": 0.93796, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001268658, "min": 0.0001268658, "max": 0.004792515800000001, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005074632, "min": 0.0005074632, "max": 0.021904204, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.704545454545453, "min": 3.1818181818181817, "max": 25.704545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1131.0, "min": 70.0, "max": 1378.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.704545454545453, "min": 3.1818181818181817, "max": 25.704545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1131.0, "min": 70.0, "max": 1378.0, "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": "1679761884", "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 --resume", "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": "1679762347" }, "total": 463.17037403099994, "count": 1, "self": 0.43105761699985123, "children": { "run_training.setup": { "total": 0.10540425099998174, "count": 1, "self": 0.10540425099998174 }, "TrainerController.start_learning": { "total": 462.6339121630001, "count": 1, "self": 0.5867048149959828, "children": { "TrainerController._reset_env": { "total": 5.944527345000097, "count": 1, "self": 5.944527345000097 }, "TrainerController.advance": { "total": 455.96854212000403, "count": 17737, "self": 0.3253818390219294, "children": { "env_step": { "total": 455.6431602809821, "count": 17737, "self": 328.5171771879816, "children": { "SubprocessEnvManager._take_step": { "total": 126.83280138098235, "count": 17737, "self": 2.3277883179878245, "children": { "TorchPolicy.evaluate": { "total": 124.50501306299452, "count": 17737, "self": 124.50501306299452 } } }, "workers": { "total": 0.2931817120181677, "count": 17737, "self": 0.0, "children": { "worker_root": { "total": 461.0009280790043, "count": 17737, "is_parallel": true, "self": 214.96186385500232, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0027792089999820746, "count": 1, "is_parallel": true, "self": 0.000728120999838211, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020510880001438636, "count": 10, "is_parallel": true, "self": 0.0020510880001438636 } } }, "UnityEnvironment.step": { "total": 0.04824274600014178, "count": 1, "is_parallel": true, "self": 0.0005894910000279197, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038546900009350793, "count": 1, "is_parallel": true, "self": 0.00038546900009350793 }, "communicator.exchange": { "total": 0.04512782699998752, "count": 1, "is_parallel": true, "self": 0.04512782699998752 }, "steps_from_proto": { "total": 0.0021399590000328317, "count": 1, "is_parallel": true, "self": 0.0005973410004571633, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015426179995756684, "count": 10, "is_parallel": true, "self": 0.0015426179995756684 } } } } } } }, "UnityEnvironment.step": { "total": 246.039064224002, "count": 17736, "is_parallel": true, "self": 9.403280328034043, "children": { "UnityEnvironment._generate_step_input": { "total": 5.098721370994781, "count": 17736, "is_parallel": true, "self": 5.098721370994781 }, "communicator.exchange": { "total": 200.8669338079908, "count": 17736, "is_parallel": true, "self": 200.8669338079908 }, "steps_from_proto": { "total": 30.67012871698239, "count": 17736, "is_parallel": true, "self": 6.321889531904844, "children": { "_process_rank_one_or_two_observation": { "total": 24.348239185077546, "count": 177360, "is_parallel": true, "self": 24.348239185077546 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.6843000088992994e-05, "count": 1, "self": 3.6843000088992994e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 452.60676231104935, "count": 420773, "is_parallel": true, "self": 9.976955237974153, "children": { "process_trajectory": { "total": 252.97012494807495, "count": 420773, "is_parallel": true, "self": 252.15448749207508, "children": { "RLTrainer._checkpoint": { "total": 0.8156374559998767, "count": 4, "is_parallel": true, "self": 0.8156374559998767 } } }, "_update_policy": { "total": 189.65968212500024, "count": 88, "is_parallel": true, "self": 68.43871314200942, "children": { "TorchPPOOptimizer.update": { "total": 121.22096898299083, "count": 4485, "is_parallel": true, "self": 121.22096898299083 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13410103999990497, "count": 1, "self": 0.001158266999937041, "children": { "RLTrainer._checkpoint": { "total": 0.13294277299996793, "count": 1, "self": 0.13294277299996793 } } } } } } }