ramsi-k's picture
First Push
cf8c2ca verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.7957823276519775,
"min": 2.7957823276519775,
"max": 2.87021541595459,
"count": 2
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 28785.375,
"min": 28785.375,
"max": 29393.875,
"count": 2
},
"SnowballTarget.Step.mean": {
"value": 19992.0,
"min": 9952.0,
"max": 19992.0,
"count": 2
},
"SnowballTarget.Step.sum": {
"value": 19992.0,
"min": 9952.0,
"max": 19992.0,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 1.225663185119629,
"min": 0.31984859704971313,
"max": 1.225663185119629,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 251.26095581054688,
"min": 62.050628662109375,
"max": 251.26095581054688,
"count": 2
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 2
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 2
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06613049754666338,
"min": 0.06613049754666338,
"max": 0.06729291869876261,
"count": 2
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3306524877333169,
"min": 0.26917167479505044,
"max": 0.3306524877333169,
"count": 2
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20845892280340195,
"min": 0.1369612846071558,
"max": 0.20845892280340195,
"count": 2
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.0422946140170097,
"min": 0.5478451384286231,
"max": 1.0422946140170097,
"count": 2
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 7.032007656e-05,
"min": 7.032007656e-05,
"max": 0.00021882002706000002,
"count": 2
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.0003516003828,
"min": 0.0003516003828,
"max": 0.0008752801082400001,
"count": 2
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.12344000000000002,
"min": 0.12344000000000002,
"max": 0.17294,
"count": 2
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.6172000000000001,
"min": 0.6172000000000001,
"max": 0.69176,
"count": 2
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0011796560000000003,
"min": 0.0011796560000000003,
"max": 0.003649706,
"count": 2
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.005898280000000001,
"min": 0.005898280000000001,
"max": 0.014598824,
"count": 2
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 5.7272727272727275,
"min": 3.727272727272727,
"max": 5.7272727272727275,
"count": 2
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 315.0,
"min": 164.0,
"max": 315.0,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 5.7272727272727275,
"min": 3.727272727272727,
"max": 5.7272727272727275,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 315.0,
"min": 164.0,
"max": 315.0,
"count": 2
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 2
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 2
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1707230012",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1707230066"
},
"total": 54.93778134699994,
"count": 1,
"self": 0.5512783799999852,
"children": {
"run_training.setup": {
"total": 0.04959871799997018,
"count": 1,
"self": 0.04959871799997018
},
"TrainerController.start_learning": {
"total": 54.336904248999986,
"count": 1,
"self": 0.100154139000324,
"children": {
"TrainerController._reset_env": {
"total": 3.0120673029999807,
"count": 1,
"self": 3.0120673029999807
},
"TrainerController.advance": {
"total": 51.11327094799958,
"count": 1872,
"self": 0.03852957199580942,
"children": {
"env_step": {
"total": 51.07474137600377,
"count": 1872,
"self": 32.55513062700368,
"children": {
"SubprocessEnvManager._take_step": {
"total": 18.485589611001387,
"count": 1872,
"self": 0.1698483809990421,
"children": {
"TorchPolicy.evaluate": {
"total": 18.315741230002345,
"count": 1872,
"self": 18.315741230002345
}
}
},
"workers": {
"total": 0.03402113799870676,
"count": 1872,
"self": 0.0,
"children": {
"worker_root": {
"total": 54.131616002997816,
"count": 1872,
"is_parallel": true,
"self": 28.45135145899735,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005851097000004302,
"count": 1,
"is_parallel": true,
"self": 0.004062359999807086,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017887370001972158,
"count": 10,
"is_parallel": true,
"self": 0.0017887370001972158
}
}
},
"UnityEnvironment.step": {
"total": 0.0425161800000069,
"count": 1,
"is_parallel": true,
"self": 0.0006856909999441996,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004291789999797402,
"count": 1,
"is_parallel": true,
"self": 0.0004291789999797402
},
"communicator.exchange": {
"total": 0.0392899320000879,
"count": 1,
"is_parallel": true,
"self": 0.0392899320000879
},
"steps_from_proto": {
"total": 0.0021113779999950566,
"count": 1,
"is_parallel": true,
"self": 0.0004124469999169378,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016989310000781188,
"count": 10,
"is_parallel": true,
"self": 0.0016989310000781188
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 25.680264544000465,
"count": 1871,
"is_parallel": true,
"self": 1.1877720270024383,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.6178653810005699,
"count": 1871,
"is_parallel": true,
"self": 0.6178653810005699
},
"communicator.exchange": {
"total": 19.97604673999831,
"count": 1871,
"is_parallel": true,
"self": 19.97604673999831
},
"steps_from_proto": {
"total": 3.898580395999147,
"count": 1871,
"is_parallel": true,
"self": 0.7545944929906909,
"children": {
"_process_rank_one_or_two_observation": {
"total": 3.1439859030084563,
"count": 18710,
"is_parallel": true,
"self": 3.1439859030084563
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0004420800000843883,
"count": 1,
"self": 0.0004420800000843883,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 50.48248829997647,
"count": 78044,
"is_parallel": true,
"self": 1.7453491659692872,
"children": {
"process_trajectory": {
"total": 28.710398274006934,
"count": 78044,
"is_parallel": true,
"self": 28.138871941007096,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5715263329998379,
"count": 4,
"is_parallel": true,
"self": 0.5715263329998379
}
}
},
"_update_policy": {
"total": 20.026740860000245,
"count": 9,
"is_parallel": true,
"self": 5.178641083001935,
"children": {
"TorchPPOOptimizer.update": {
"total": 14.84809977699831,
"count": 456,
"is_parallel": true,
"self": 14.84809977699831
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11096977900001548,
"count": 1,
"self": 0.001278330999980426,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10969144800003505,
"count": 1,
"self": 0.10969144800003505
}
}
}
}
}
}
}