irgallard's picture
First Push
4d30208
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9388682842254639,
"min": 0.9388682842254639,
"max": 2.8630309104919434,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8995.296875,
"min": 8995.296875,
"max": 29383.28515625,
"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": 12.976569175720215,
"min": 0.28020739555358887,
"max": 12.976569175720215,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2530.430908203125,
"min": 54.36023712158203,
"max": 2637.3671875,
"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": 0.0642304686333791,
"min": 0.061750990194388365,
"max": 0.0762051928545321,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2569218745335164,
"min": 0.24700396077755346,
"max": 0.37332956843174003,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18999334768045184,
"min": 0.12336772993006105,
"max": 0.2682700956276819,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7599733907218074,
"min": 0.4934709197202442,
"max": 1.3229054478453657,
"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": 25.386363636363637,
"min": 3.227272727272727,
"max": 25.386363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1117.0,
"min": 142.0,
"max": 1386.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.386363636363637,
"min": 3.227272727272727,
"max": 25.386363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1117.0,
"min": 142.0,
"max": 1386.0,
"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": "1681724036",
"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",
"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": "1681724486"
},
"total": 449.7300791000001,
"count": 1,
"self": 0.43170046200020806,
"children": {
"run_training.setup": {
"total": 0.11590266799998972,
"count": 1,
"self": 0.11590266799998972
},
"TrainerController.start_learning": {
"total": 449.1824759699999,
"count": 1,
"self": 0.5164681040055257,
"children": {
"TrainerController._reset_env": {
"total": 3.849620179999988,
"count": 1,
"self": 3.849620179999988
},
"TrainerController.advance": {
"total": 444.68665102199475,
"count": 18205,
"self": 0.2708006229960347,
"children": {
"env_step": {
"total": 444.4158503989987,
"count": 18205,
"self": 326.8109505680004,
"children": {
"SubprocessEnvManager._take_step": {
"total": 117.3496463769925,
"count": 18205,
"self": 1.6531976419876173,
"children": {
"TorchPolicy.evaluate": {
"total": 115.69644873500488,
"count": 18205,
"self": 115.69644873500488
}
}
},
"workers": {
"total": 0.25525345400581045,
"count": 18205,
"self": 0.0,
"children": {
"worker_root": {
"total": 447.7420753579854,
"count": 18205,
"is_parallel": true,
"self": 207.89038297498064,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005654567000078714,
"count": 1,
"is_parallel": true,
"self": 0.0040746240001681144,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015799429999105996,
"count": 10,
"is_parallel": true,
"self": 0.0015799429999105996
}
}
},
"UnityEnvironment.step": {
"total": 0.04272509400004765,
"count": 1,
"is_parallel": true,
"self": 0.0005900420002262763,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003778089999286749,
"count": 1,
"is_parallel": true,
"self": 0.0003778089999286749
},
"communicator.exchange": {
"total": 0.039851318999922114,
"count": 1,
"is_parallel": true,
"self": 0.039851318999922114
},
"steps_from_proto": {
"total": 0.0019059239999705824,
"count": 1,
"is_parallel": true,
"self": 0.0003916889996844475,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015142350002861349,
"count": 10,
"is_parallel": true,
"self": 0.0015142350002861349
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 239.85169238300477,
"count": 18204,
"is_parallel": true,
"self": 9.80325341100911,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.279905595995956,
"count": 18204,
"is_parallel": true,
"self": 5.279905595995956
},
"communicator.exchange": {
"total": 193.69902378099948,
"count": 18204,
"is_parallel": true,
"self": 193.69902378099948
},
"steps_from_proto": {
"total": 31.069509595000227,
"count": 18204,
"is_parallel": true,
"self": 6.085658551056895,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.983851043943332,
"count": 182040,
"is_parallel": true,
"self": 24.983851043943332
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00010884599987548427,
"count": 1,
"self": 0.00010884599987548427,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 441.4109828950077,
"count": 383914,
"is_parallel": true,
"self": 9.760406122025756,
"children": {
"process_trajectory": {
"total": 242.9050474449814,
"count": 383914,
"is_parallel": true,
"self": 241.32579562198111,
"children": {
"RLTrainer._checkpoint": {
"total": 1.579251823000277,
"count": 4,
"is_parallel": true,
"self": 1.579251823000277
}
}
},
"_update_policy": {
"total": 188.74552932800054,
"count": 90,
"is_parallel": true,
"self": 70.54693506500894,
"children": {
"TorchPPOOptimizer.update": {
"total": 118.1985942629916,
"count": 4587,
"is_parallel": true,
"self": 118.1985942629916
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12962781799978984,
"count": 1,
"self": 0.0008839559998250479,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1287438619999648,
"count": 1,
"self": 0.1287438619999648
}
}
}
}
}
}
}