Gaivoronsky's picture
First Push
b177022
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9347748756408691,
"min": 0.9347748756408691,
"max": 2.870821237564087,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8925.23046875,
"min": 8925.23046875,
"max": 29431.658203125,
"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": 13.051813125610352,
"min": 0.40046122670173645,
"max": 13.051813125610352,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2545.103515625,
"min": 77.6894760131836,
"max": 2626.13916015625,
"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": 0.06582016309988045,
"min": 0.06301620793180751,
"max": 0.07173947486632695,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2632806523995218,
"min": 0.25206483172723004,
"max": 0.3586973743316348,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1848845719268509,
"min": 0.13145641689006166,
"max": 0.2922152230552598,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7395382877074036,
"min": 0.5258256675602466,
"max": 1.4610761152762992,
"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": 26.386363636363637,
"min": 3.2954545454545454,
"max": 26.386363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1161.0,
"min": 145.0,
"max": 1410.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.386363636363637,
"min": 3.2954545454545454,
"max": 26.386363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1161.0,
"min": 145.0,
"max": 1410.0,
"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": "1684854693",
"python_version": "3.10.6 (main, Mar 10 2023, 10:55:28) [GCC 11.3.0]",
"command_line_arguments": "/home/alex/.local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu113",
"numpy_version": "1.21.2",
"end_time_seconds": "1684854911"
},
"total": 217.974715048,
"count": 1,
"self": 0.31908150799995383,
"children": {
"run_training.setup": {
"total": 0.009028280000052291,
"count": 1,
"self": 0.009028280000052291
},
"TrainerController.start_learning": {
"total": 217.64660526,
"count": 1,
"self": 0.35975305700105764,
"children": {
"TrainerController._reset_env": {
"total": 5.921296913999981,
"count": 1,
"self": 5.921296913999981
},
"TrainerController.advance": {
"total": 211.29437028099903,
"count": 18203,
"self": 0.19730869699412779,
"children": {
"env_step": {
"total": 211.0970615840049,
"count": 18203,
"self": 144.734286379016,
"children": {
"SubprocessEnvManager._take_step": {
"total": 66.16749756399395,
"count": 18203,
"self": 0.969686294990538,
"children": {
"TorchPolicy.evaluate": {
"total": 65.19781126900341,
"count": 18203,
"self": 65.19781126900341
}
}
},
"workers": {
"total": 0.19527764099495926,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 217.23435935799557,
"count": 18203,
"is_parallel": true,
"self": 114.45250543799409,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009598080000614573,
"count": 1,
"is_parallel": true,
"self": 0.00024892700002965285,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007108810000318044,
"count": 10,
"is_parallel": true,
"self": 0.0007108810000318044
}
}
},
"UnityEnvironment.step": {
"total": 0.0214716950000593,
"count": 1,
"is_parallel": true,
"self": 0.00022902200009866647,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019200299993826775,
"count": 1,
"is_parallel": true,
"self": 0.00019200299993826775
},
"communicator.exchange": {
"total": 0.020242983999992248,
"count": 1,
"is_parallel": true,
"self": 0.020242983999992248
},
"steps_from_proto": {
"total": 0.0008076860000301167,
"count": 1,
"is_parallel": true,
"self": 0.0001799890000029336,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006276970000271831,
"count": 10,
"is_parallel": true,
"self": 0.0006276970000271831
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 102.78185392000148,
"count": 18202,
"is_parallel": true,
"self": 4.49393466698416,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.549921165006367,
"count": 18202,
"is_parallel": true,
"self": 2.549921165006367
},
"communicator.exchange": {
"total": 81.53672325901357,
"count": 18202,
"is_parallel": true,
"self": 81.53672325901357
},
"steps_from_proto": {
"total": 14.201274828997384,
"count": 18202,
"is_parallel": true,
"self": 3.0012425939977447,
"children": {
"_process_rank_one_or_two_observation": {
"total": 11.20003223499964,
"count": 182020,
"is_parallel": true,
"self": 11.20003223499964
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.7773999995115446e-05,
"count": 1,
"self": 4.7773999995115446e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 210.7673682289685,
"count": 186339,
"is_parallel": true,
"self": 1.9597381369794675,
"children": {
"process_trajectory": {
"total": 109.65982094098888,
"count": 186339,
"is_parallel": true,
"self": 109.25140383498899,
"children": {
"RLTrainer._checkpoint": {
"total": 0.408417105999888,
"count": 4,
"is_parallel": true,
"self": 0.408417105999888
}
}
},
"_update_policy": {
"total": 99.14780915100016,
"count": 90,
"is_parallel": true,
"self": 27.888865099996337,
"children": {
"TorchPPOOptimizer.update": {
"total": 71.25894405100382,
"count": 4587,
"is_parallel": true,
"self": 71.25894405100382
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.07113723399993432,
"count": 1,
"self": 0.0005538009999099813,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07058343300002434,
"count": 1,
"self": 0.07058343300002434
}
}
}
}
}
}
}