GillesEverling's picture
First Push
0e9b875
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.991176426410675,
"min": 0.991176426410675,
"max": 2.8517684936523438,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9474.6552734375,
"min": 9474.6552734375,
"max": 29204.9609375,
"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": 13.070467948913574,
"min": 0.2564752995967865,
"max": 13.070467948913574,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2548.7412109375,
"min": 49.75621032714844,
"max": 2634.38330078125,
"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": 0.06237886827604562,
"min": 0.06237886827604562,
"max": 0.07428964065072839,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24951547310418248,
"min": 0.24951547310418248,
"max": 0.371448203253642,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1873985501188858,
"min": 0.12830366529227583,
"max": 0.29059492513245233,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7495942004755431,
"min": 0.5132146611691033,
"max": 1.4529746256622615,
"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": 26.227272727272727,
"min": 3.2045454545454546,
"max": 26.227272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1154.0,
"min": 141.0,
"max": 1418.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.227272727272727,
"min": 3.2045454545454546,
"max": 26.227272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1154.0,
"min": 141.0,
"max": 1418.0,
"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": "1681392337",
"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": "1681392799"
},
"total": 462.36466183999994,
"count": 1,
"self": 0.7595360939998841,
"children": {
"run_training.setup": {
"total": 0.11337852700000894,
"count": 1,
"self": 0.11337852700000894
},
"TrainerController.start_learning": {
"total": 461.49174721900005,
"count": 1,
"self": 0.5576943479964029,
"children": {
"TrainerController._reset_env": {
"total": 3.6807325710000214,
"count": 1,
"self": 3.6807325710000214
},
"TrainerController.advance": {
"total": 457.0329595830037,
"count": 18223,
"self": 0.2806048790037039,
"children": {
"env_step": {
"total": 456.75235470399997,
"count": 18223,
"self": 333.6701757060155,
"children": {
"SubprocessEnvManager._take_step": {
"total": 122.8070270309866,
"count": 18223,
"self": 1.8388702499861438,
"children": {
"TorchPolicy.evaluate": {
"total": 120.96815678100046,
"count": 18223,
"self": 120.96815678100046
}
}
},
"workers": {
"total": 0.2751519669978393,
"count": 18223,
"self": 0.0,
"children": {
"worker_root": {
"total": 459.88640767099855,
"count": 18223,
"is_parallel": true,
"self": 214.4559793739964,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004934599000023354,
"count": 1,
"is_parallel": true,
"self": 0.003371714000081738,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015628849999416161,
"count": 10,
"is_parallel": true,
"self": 0.0015628849999416161
}
}
},
"UnityEnvironment.step": {
"total": 0.037585464999949636,
"count": 1,
"is_parallel": true,
"self": 0.0006709479999358336,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003803960000254847,
"count": 1,
"is_parallel": true,
"self": 0.0003803960000254847
},
"communicator.exchange": {
"total": 0.034581503999959295,
"count": 1,
"is_parallel": true,
"self": 0.034581503999959295
},
"steps_from_proto": {
"total": 0.0019526170000290222,
"count": 1,
"is_parallel": true,
"self": 0.0003974480000579206,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015551689999711016,
"count": 10,
"is_parallel": true,
"self": 0.0015551689999711016
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 245.43042829700215,
"count": 18222,
"is_parallel": true,
"self": 9.891804763002767,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.533461239003088,
"count": 18222,
"is_parallel": true,
"self": 5.533461239003088
},
"communicator.exchange": {
"total": 197.60183374500036,
"count": 18222,
"is_parallel": true,
"self": 197.60183374500036
},
"steps_from_proto": {
"total": 32.40332854999593,
"count": 18222,
"is_parallel": true,
"self": 6.439595551005539,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.963732998990395,
"count": 182220,
"is_parallel": true,
"self": 25.963732998990395
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011495499995817227,
"count": 1,
"self": 0.00011495499995817227,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 453.6829576330802,
"count": 402916,
"is_parallel": true,
"self": 9.7868510311053,
"children": {
"process_trajectory": {
"total": 250.07223986897571,
"count": 402916,
"is_parallel": true,
"self": 248.23370901497577,
"children": {
"RLTrainer._checkpoint": {
"total": 1.8385308539999414,
"count": 4,
"is_parallel": true,
"self": 1.8385308539999414
}
}
},
"_update_policy": {
"total": 193.8238667329992,
"count": 90,
"is_parallel": true,
"self": 73.29524171700638,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.52862501599282,
"count": 4587,
"is_parallel": true,
"self": 120.52862501599282
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.22024576199999046,
"count": 1,
"self": 0.0011433820000092965,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21910237999998117,
"count": 1,
"self": 0.21910237999998117
}
}
}
}
}
}
}