IvanKhoma's picture
another try
6c0e109 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.740505576133728,
"min": 0.7179226875305176,
"max": 2.8826167583465576,
"count": 100
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7045.91064453125,
"min": 6883.1787109375,
"max": 29679.421875,
"count": 100
},
"SnowballTarget.Step.mean": {
"value": 999952.0,
"min": 9952.0,
"max": 999952.0,
"count": 100
},
"SnowballTarget.Step.sum": {
"value": 999952.0,
"min": 9952.0,
"max": 999952.0,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6586428880691528,
"min": 0.07228649407625198,
"max": 0.6803814768791199,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 128.43536376953125,
"min": 14.023579597473145,
"max": 139.02691650390625,
"count": 100
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 100
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 100
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07097117919075732,
"min": 0.061910840123207043,
"max": 0.07258502758231342,
"count": 100
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2838847167630293,
"min": 0.24764336049282817,
"max": 0.3629251379115671,
"count": 100
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.06467204483992914,
"min": 0.02632609400761259,
"max": 0.08109224807909307,
"count": 100
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.25868817935971655,
"min": 0.10530437603045036,
"max": 0.4043472061700681,
"count": 100
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.3764995412000025e-06,
"min": 1.3764995412000025e-06,
"max": 0.0002983764005412,
"count": 100
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.50599816480001e-06,
"min": 5.50599816480001e-06,
"max": 0.0014770320076559996,
"count": 100
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10045880000000001,
"min": 0.10045880000000001,
"max": 0.19945880000000002,
"count": 100
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.40183520000000006,
"min": 0.40183520000000006,
"max": 0.9923440000000001,
"count": 100
},
"SnowballTarget.Policy.Beta.mean": {
"value": 3.289412000000005e-05,
"min": 3.289412000000005e-05,
"max": 0.004972994119999999,
"count": 100
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0001315764800000002,
"min": 0.0001315764800000002,
"max": 0.024617965600000007,
"count": 100
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.755555555555556,
"min": 2.727272727272727,
"max": 26.618181818181817,
"count": 100
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1159.0,
"min": 120.0,
"max": 1464.0,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.755555555555556,
"min": 2.727272727272727,
"max": 26.618181818181817,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1159.0,
"min": 120.0,
"max": 1464.0,
"count": 100
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1721294554",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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=SnowballTarget6 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1721297620"
},
"total": 3065.7011201230002,
"count": 1,
"self": 1.3339028690002124,
"children": {
"run_training.setup": {
"total": 0.07040079300003299,
"count": 1,
"self": 0.07040079300003299
},
"TrainerController.start_learning": {
"total": 3064.296816461,
"count": 1,
"self": 4.029628481008331,
"children": {
"TrainerController._reset_env": {
"total": 2.8787076229999684,
"count": 1,
"self": 2.8787076229999684
},
"TrainerController.advance": {
"total": 3057.2625425169913,
"count": 90939,
"self": 2.1185516130594806,
"children": {
"env_step": {
"total": 3055.143990903932,
"count": 90939,
"self": 2361.2746848469315,
"children": {
"SubprocessEnvManager._take_step": {
"total": 691.8183277430346,
"count": 90939,
"self": 11.517796144053136,
"children": {
"TorchPolicy.evaluate": {
"total": 680.3005315989815,
"count": 90939,
"self": 680.3005315989815
}
}
},
"workers": {
"total": 2.0509783139654587,
"count": 90939,
"self": 0.0,
"children": {
"worker_root": {
"total": 3054.310742156016,
"count": 90939,
"is_parallel": true,
"self": 1483.2500732140993,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006115685999986908,
"count": 1,
"is_parallel": true,
"self": 0.004304450999939036,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018112350000478727,
"count": 10,
"is_parallel": true,
"self": 0.0018112350000478727
}
}
},
"UnityEnvironment.step": {
"total": 0.04233680400000139,
"count": 1,
"is_parallel": true,
"self": 0.000887555999952383,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047182200000861485,
"count": 1,
"is_parallel": true,
"self": 0.00047182200000861485
},
"communicator.exchange": {
"total": 0.03865661600002568,
"count": 1,
"is_parallel": true,
"self": 0.03865661600002568
},
"steps_from_proto": {
"total": 0.002320810000014717,
"count": 1,
"is_parallel": true,
"self": 0.0004447619999723429,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001876048000042374,
"count": 10,
"is_parallel": true,
"self": 0.001876048000042374
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1571.060668941917,
"count": 90938,
"is_parallel": true,
"self": 75.11316666099174,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 38.0692610069766,
"count": 90938,
"is_parallel": true,
"self": 38.0692610069766
},
"communicator.exchange": {
"total": 1235.9001557129504,
"count": 90938,
"is_parallel": true,
"self": 1235.9001557129504
},
"steps_from_proto": {
"total": 221.97808556099818,
"count": 90938,
"is_parallel": true,
"self": 43.91011916704326,
"children": {
"_process_rank_one_or_two_observation": {
"total": 178.06796639395492,
"count": 909380,
"is_parallel": true,
"self": 178.06796639395492
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0003927690004275064,
"count": 1,
"self": 0.0003927690004275064,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 3021.922174456896,
"count": 4011405,
"is_parallel": true,
"self": 89.56384776008872,
"children": {
"process_trajectory": {
"total": 1535.5047238928123,
"count": 4011405,
"is_parallel": true,
"self": 1531.6284534898125,
"children": {
"RLTrainer._checkpoint": {
"total": 3.8762704029998076,
"count": 20,
"is_parallel": true,
"self": 3.8762704029998076
}
}
},
"_update_policy": {
"total": 1396.853602803995,
"count": 454,
"is_parallel": true,
"self": 572.9278461920408,
"children": {
"TorchPPOOptimizer.update": {
"total": 823.9257566119543,
"count": 38585,
"is_parallel": true,
"self": 823.9257566119543
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1255450710000332,
"count": 1,
"self": 0.0011320509997858608,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12441302000024734,
"count": 1,
"self": 0.12441302000024734
}
}
}
}
}
}
}