IWR's picture
First Push
4585f5f
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9271471500396729,
"min": 0.9271471500396729,
"max": 2.8703079223632812,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8862.599609375,
"min": 8862.599609375,
"max": 29457.970703125,
"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": 13.126503944396973,
"min": 0.260244220495224,
"max": 13.126503944396973,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2559.668212890625,
"min": 50.48737716674805,
"max": 2669.51318359375,
"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": 0.07243584130350535,
"min": 0.060619179693115734,
"max": 0.07361890372589651,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2897433652140214,
"min": 0.24247671877246293,
"max": 0.3593976617463769,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19631777177838716,
"min": 0.1163079292666368,
"max": 0.2857237844636627,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7852710871135486,
"min": 0.4652317170665472,
"max": 1.4144963774026609,
"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": 25.954545454545453,
"min": 3.340909090909091,
"max": 25.954545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1142.0,
"min": 147.0,
"max": 1411.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.954545454545453,
"min": 3.340909090909091,
"max": 25.954545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1142.0,
"min": 147.0,
"max": 1411.0,
"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": "1696244676",
"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": "1696245143"
},
"total": 467.4893530920001,
"count": 1,
"self": 0.43798995100019056,
"children": {
"run_training.setup": {
"total": 0.06607495000002928,
"count": 1,
"self": 0.06607495000002928
},
"TrainerController.start_learning": {
"total": 466.9852881909999,
"count": 1,
"self": 0.5186509389948242,
"children": {
"TrainerController._reset_env": {
"total": 4.854221691000021,
"count": 1,
"self": 4.854221691000021
},
"TrainerController.advance": {
"total": 461.4744517110048,
"count": 18202,
"self": 0.2582282790181125,
"children": {
"env_step": {
"total": 461.2162234319867,
"count": 18202,
"self": 338.53414164397145,
"children": {
"SubprocessEnvManager._take_step": {
"total": 122.41302196699553,
"count": 18202,
"self": 1.6694823789835027,
"children": {
"TorchPolicy.evaluate": {
"total": 120.74353958801203,
"count": 18202,
"self": 120.74353958801203
}
}
},
"workers": {
"total": 0.2690598210197095,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 465.33026675599285,
"count": 18202,
"is_parallel": true,
"self": 221.47390876299232,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007858772999952635,
"count": 1,
"is_parallel": true,
"self": 0.005444255000384146,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0024145179995684884,
"count": 10,
"is_parallel": true,
"self": 0.0024145179995684884
}
}
},
"UnityEnvironment.step": {
"total": 0.03793625100001918,
"count": 1,
"is_parallel": true,
"self": 0.000617802000078882,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003243610001391062,
"count": 1,
"is_parallel": true,
"self": 0.0003243610001391062
},
"communicator.exchange": {
"total": 0.03391091499997856,
"count": 1,
"is_parallel": true,
"self": 0.03391091499997856
},
"steps_from_proto": {
"total": 0.0030831729998226365,
"count": 1,
"is_parallel": true,
"self": 0.00037974300016685447,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002703429999655782,
"count": 10,
"is_parallel": true,
"self": 0.002703429999655782
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 243.85635799300053,
"count": 18201,
"is_parallel": true,
"self": 10.468843976998187,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.231472287015777,
"count": 18201,
"is_parallel": true,
"self": 5.231472287015777
},
"communicator.exchange": {
"total": 192.57705859298903,
"count": 18201,
"is_parallel": true,
"self": 192.57705859298903
},
"steps_from_proto": {
"total": 35.57898313599753,
"count": 18201,
"is_parallel": true,
"self": 6.403574246047356,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.175408889950177,
"count": 182010,
"is_parallel": true,
"self": 29.175408889950177
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001280080000469752,
"count": 1,
"self": 0.0001280080000469752,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 458.0090753580239,
"count": 417177,
"is_parallel": true,
"self": 9.59484239501171,
"children": {
"process_trajectory": {
"total": 247.1139706380102,
"count": 417177,
"is_parallel": true,
"self": 246.31798115000993,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7959894880002594,
"count": 4,
"is_parallel": true,
"self": 0.7959894880002594
}
}
},
"_update_policy": {
"total": 201.300262325002,
"count": 90,
"is_parallel": true,
"self": 85.78113017200576,
"children": {
"TorchPPOOptimizer.update": {
"total": 115.51913215299624,
"count": 4584,
"is_parallel": true,
"self": 115.51913215299624
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13783584200018595,
"count": 1,
"self": 0.0008125180002025445,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1370233239999834,
"count": 1,
"self": 0.1370233239999834
}
}
}
}
}
}
}