jamesthong's picture
First Push
2cd239f
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.910214364528656,
"min": 0.8915772438049316,
"max": 2.8725104331970215,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8690.7265625,
"min": 8690.7265625,
"max": 29417.37890625,
"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": 13.263171195983887,
"min": 0.23914745450019836,
"max": 13.263171195983887,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2586.318359375,
"min": 46.39460754394531,
"max": 2702.580078125,
"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": 0.06522045991080043,
"min": 0.06356040325399769,
"max": 0.07325751281642429,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2608818396432017,
"min": 0.25424161301599074,
"max": 0.35525161911066916,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1826438230334544,
"min": 0.11200561100050954,
"max": 0.29257841232944937,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7305752921338176,
"min": 0.44802244400203817,
"max": 1.462892061647247,
"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": 25.431818181818183,
"min": 2.9318181818181817,
"max": 26.01818181818182,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1119.0,
"min": 129.0,
"max": 1431.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.431818181818183,
"min": 2.9318181818181817,
"max": 26.01818181818182,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1119.0,
"min": 129.0,
"max": 1431.0,
"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": "1677069537",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.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": "1677069979"
},
"total": 441.9853115839999,
"count": 1,
"self": 0.4337291109998205,
"children": {
"run_training.setup": {
"total": 0.1670557130000816,
"count": 1,
"self": 0.1670557130000816
},
"TrainerController.start_learning": {
"total": 441.38452675999997,
"count": 1,
"self": 0.5224417180047567,
"children": {
"TrainerController._reset_env": {
"total": 9.12920856400001,
"count": 1,
"self": 9.12920856400001
},
"TrainerController.advance": {
"total": 431.60741505999545,
"count": 18201,
"self": 0.2496235940209317,
"children": {
"env_step": {
"total": 431.3577914659745,
"count": 18201,
"self": 295.5236565039636,
"children": {
"SubprocessEnvManager._take_step": {
"total": 135.57200970297026,
"count": 18201,
"self": 1.5261071679492488,
"children": {
"TorchPolicy.evaluate": {
"total": 134.045902535021,
"count": 18201,
"self": 30.317065409018596,
"children": {
"TorchPolicy.sample_actions": {
"total": 103.72883712600242,
"count": 18201,
"self": 103.72883712600242
}
}
}
}
},
"workers": {
"total": 0.2621252590406584,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 440.11755543500453,
"count": 18201,
"is_parallel": true,
"self": 213.16469560500218,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0066055800000413,
"count": 1,
"is_parallel": true,
"self": 0.0034936969998398126,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0031118830002014874,
"count": 10,
"is_parallel": true,
"self": 0.0031118830002014874
}
}
},
"UnityEnvironment.step": {
"total": 0.03779560800012405,
"count": 1,
"is_parallel": true,
"self": 0.0005406990001119993,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00029158500001358334,
"count": 1,
"is_parallel": true,
"self": 0.00029158500001358334
},
"communicator.exchange": {
"total": 0.03515708400004769,
"count": 1,
"is_parallel": true,
"self": 0.03515708400004769
},
"steps_from_proto": {
"total": 0.0018062399999507761,
"count": 1,
"is_parallel": true,
"self": 0.0004392209996240126,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013670190003267635,
"count": 10,
"is_parallel": true,
"self": 0.0013670190003267635
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 226.95285983000235,
"count": 18200,
"is_parallel": true,
"self": 9.160410839962879,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.942069825026465,
"count": 18200,
"is_parallel": true,
"self": 4.942069825026465
},
"communicator.exchange": {
"total": 182.84216126403248,
"count": 18200,
"is_parallel": true,
"self": 182.84216126403248
},
"steps_from_proto": {
"total": 30.008217900980526,
"count": 18200,
"is_parallel": true,
"self": 6.34869969194483,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.659518209035696,
"count": 182000,
"is_parallel": true,
"self": 23.659518209035696
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014121799995336914,
"count": 1,
"self": 0.00014121799995336914,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 428.23331220590717,
"count": 399082,
"is_parallel": true,
"self": 9.516262975975224,
"children": {
"process_trajectory": {
"total": 246.44277426393114,
"count": 399082,
"is_parallel": true,
"self": 245.29964265693138,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1431316069997592,
"count": 4,
"is_parallel": true,
"self": 1.1431316069997592
}
}
},
"_update_policy": {
"total": 172.2742749660008,
"count": 90,
"is_parallel": true,
"self": 62.11235771701172,
"children": {
"TorchPPOOptimizer.update": {
"total": 110.16191724898908,
"count": 4587,
"is_parallel": true,
"self": 110.16191724898908
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12532019999980548,
"count": 1,
"self": 0.0008569599995098542,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12446324000029563,
"count": 1,
"self": 0.12446324000029563
}
}
}
}
}
}
}