guydebruyn's picture
First Push
4095e7d
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9737901091575623,
"min": 0.9679049253463745,
"max": 2.8732645511627197,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9329.8828125,
"min": 9329.8828125,
"max": 29488.314453125,
"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": 12.657111167907715,
"min": 0.28411197662353516,
"max": 12.657111167907715,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2468.13671875,
"min": 55.11772155761719,
"max": 2557.6474609375,
"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": 0.07104201344932959,
"min": 0.0630872000388491,
"max": 0.07293436894942001,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28416805379731835,
"min": 0.25353572402131175,
"max": 0.36467184474710007,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20374962899322605,
"min": 0.12481466097090686,
"max": 0.27050723354606065,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8149985159729042,
"min": 0.49925864388362745,
"max": 1.3163851704083238,
"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": 25.136363636363637,
"min": 3.477272727272727,
"max": 25.272727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1106.0,
"min": 153.0,
"max": 1372.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.136363636363637,
"min": 3.477272727272727,
"max": 25.272727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1106.0,
"min": 153.0,
"max": 1372.0,
"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": "1694963896",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "1694964454"
},
"total": 558.4923459660001,
"count": 1,
"self": 0.533858115000271,
"children": {
"run_training.setup": {
"total": 0.07056028399995284,
"count": 1,
"self": 0.07056028399995284
},
"TrainerController.start_learning": {
"total": 557.8879275669999,
"count": 1,
"self": 0.8039140180109143,
"children": {
"TrainerController._reset_env": {
"total": 2.3080992299999252,
"count": 1,
"self": 2.3080992299999252
},
"TrainerController.advance": {
"total": 554.622039545989,
"count": 18205,
"self": 0.36290860699330096,
"children": {
"env_step": {
"total": 554.2591309389957,
"count": 18205,
"self": 454.08408901299606,
"children": {
"SubprocessEnvManager._take_step": {
"total": 99.78727591400832,
"count": 18205,
"self": 2.231424155008881,
"children": {
"TorchPolicy.evaluate": {
"total": 97.55585175899944,
"count": 18205,
"self": 97.55585175899944
}
}
},
"workers": {
"total": 0.3877660119912889,
"count": 18205,
"self": 0.0,
"children": {
"worker_root": {
"total": 555.9196141590018,
"count": 18205,
"is_parallel": true,
"self": 243.95719776399483,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008302387000071576,
"count": 1,
"is_parallel": true,
"self": 0.0052885770002149,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003013809999856676,
"count": 10,
"is_parallel": true,
"self": 0.003013809999856676
}
}
},
"UnityEnvironment.step": {
"total": 0.08767558200008807,
"count": 1,
"is_parallel": true,
"self": 0.0007213000000092507,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005114180000873603,
"count": 1,
"is_parallel": true,
"self": 0.0005114180000873603
},
"communicator.exchange": {
"total": 0.08212915500007512,
"count": 1,
"is_parallel": true,
"self": 0.08212915500007512
},
"steps_from_proto": {
"total": 0.004313708999916344,
"count": 1,
"is_parallel": true,
"self": 0.0015932969997720647,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002720412000144279,
"count": 10,
"is_parallel": true,
"self": 0.002720412000144279
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 311.9624163950069,
"count": 18204,
"is_parallel": true,
"self": 12.769795965001094,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.821478863002312,
"count": 18204,
"is_parallel": true,
"self": 6.821478863002312
},
"communicator.exchange": {
"total": 247.64608173300394,
"count": 18204,
"is_parallel": true,
"self": 247.64608173300394
},
"steps_from_proto": {
"total": 44.72505983399958,
"count": 18204,
"is_parallel": true,
"self": 8.55395590603689,
"children": {
"_process_rank_one_or_two_observation": {
"total": 36.17110392796269,
"count": 182040,
"is_parallel": true,
"self": 36.17110392796269
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016544899995096785,
"count": 1,
"self": 0.00016544899995096785,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 550.2665445499196,
"count": 521578,
"is_parallel": true,
"self": 11.998846715865966,
"children": {
"process_trajectory": {
"total": 295.84530790105316,
"count": 521578,
"is_parallel": true,
"self": 293.62564882705306,
"children": {
"RLTrainer._checkpoint": {
"total": 2.2196590740001056,
"count": 4,
"is_parallel": true,
"self": 2.2196590740001056
}
}
},
"_update_policy": {
"total": 242.42238993300043,
"count": 90,
"is_parallel": true,
"self": 96.04844476800565,
"children": {
"TorchPPOOptimizer.update": {
"total": 146.37394516499478,
"count": 4584,
"is_parallel": true,
"self": 146.37394516499478
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1537093240001468,
"count": 1,
"self": 0.0010358170002291445,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15267350699991766,
"count": 1,
"self": 0.15267350699991766
}
}
}
}
}
}
}