harshil128's picture
default training parameters
1e51564
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0647653341293335,
"min": 1.0647653341293335,
"max": 2.8712449073791504,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10166.37890625,
"min": 10166.37890625,
"max": 29436.00390625,
"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": 12.767921447753906,
"min": 0.25307074189186096,
"max": 12.767921447753906,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2489.74462890625,
"min": 49.095726013183594,
"max": 2546.99609375,
"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": 0.06977843579396475,
"min": 0.06351436892907847,
"max": 0.07309836442279857,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.279113743175859,
"min": 0.2579405740589387,
"max": 0.3651434060496589,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2012037475200772,
"min": 0.12347003974604841,
"max": 0.2736374693758347,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8048149900803088,
"min": 0.49388015898419363,
"max": 1.3681873468791736,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.106097298000005e-06,
"min": 8.106097298000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.242438919200002e-05,
"min": 3.242438919200002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10270200000000002,
"min": 0.10270200000000002,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41080800000000006,
"min": 0.41080800000000006,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00014482980000000007,
"min": 0.00014482980000000007,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005793192000000003,
"min": 0.0005793192000000003,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.34090909090909,
"min": 3.2954545454545454,
"max": 25.34090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1115.0,
"min": 145.0,
"max": 1382.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.34090909090909,
"min": 3.2954545454545454,
"max": 25.34090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1115.0,
"min": 145.0,
"max": 1382.0,
"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": "1679775639",
"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": "1679776124"
},
"total": 485.4336170329999,
"count": 1,
"self": 0.43251320199976817,
"children": {
"run_training.setup": {
"total": 0.12018766500000311,
"count": 1,
"self": 0.12018766500000311
},
"TrainerController.start_learning": {
"total": 484.88091616600013,
"count": 1,
"self": 0.5312412920063707,
"children": {
"TrainerController._reset_env": {
"total": 9.276341934000015,
"count": 1,
"self": 9.276341934000015
},
"TrainerController.advance": {
"total": 474.9363520849937,
"count": 18201,
"self": 0.2936870579906099,
"children": {
"env_step": {
"total": 474.6426650270031,
"count": 18201,
"self": 342.1027057210101,
"children": {
"SubprocessEnvManager._take_step": {
"total": 132.25657022799248,
"count": 18201,
"self": 2.0789120699929526,
"children": {
"TorchPolicy.evaluate": {
"total": 130.17765815799953,
"count": 18201,
"self": 130.17765815799953
}
}
},
"workers": {
"total": 0.2833890780004822,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 483.34985670899357,
"count": 18201,
"is_parallel": true,
"self": 232.40705297899035,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006477535000044554,
"count": 1,
"is_parallel": true,
"self": 0.004003663000048618,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0024738719999959358,
"count": 10,
"is_parallel": true,
"self": 0.0024738719999959358
}
}
},
"UnityEnvironment.step": {
"total": 0.0365664089999882,
"count": 1,
"is_parallel": true,
"self": 0.0005942449998883603,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002864790000103312,
"count": 1,
"is_parallel": true,
"self": 0.0002864790000103312
},
"communicator.exchange": {
"total": 0.033516143000042575,
"count": 1,
"is_parallel": true,
"self": 0.033516143000042575
},
"steps_from_proto": {
"total": 0.002169542000046931,
"count": 1,
"is_parallel": true,
"self": 0.0004629720000366433,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001706570000010288,
"count": 10,
"is_parallel": true,
"self": 0.001706570000010288
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 250.94280373000322,
"count": 18200,
"is_parallel": true,
"self": 9.930130073994064,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.473843733009403,
"count": 18200,
"is_parallel": true,
"self": 5.473843733009403
},
"communicator.exchange": {
"total": 201.68541888099458,
"count": 18200,
"is_parallel": true,
"self": 201.68541888099458
},
"steps_from_proto": {
"total": 33.85341104200518,
"count": 18200,
"is_parallel": true,
"self": 6.670645044005823,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.182765997999354,
"count": 182000,
"is_parallel": true,
"self": 27.182765997999354
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001530650001768663,
"count": 1,
"self": 0.0001530650001768663,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 471.1250460749718,
"count": 435118,
"is_parallel": true,
"self": 10.899652616971935,
"children": {
"process_trajectory": {
"total": 262.5105337889995,
"count": 435118,
"is_parallel": true,
"self": 261.3907108369998,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1198229519997085,
"count": 4,
"is_parallel": true,
"self": 1.1198229519997085
}
}
},
"_update_policy": {
"total": 197.71485966900036,
"count": 90,
"is_parallel": true,
"self": 73.90969823499768,
"children": {
"TorchPPOOptimizer.update": {
"total": 123.80516143400268,
"count": 4584,
"is_parallel": true,
"self": 123.80516143400268
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13682778999987022,
"count": 1,
"self": 0.0008683179999025015,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13595947199996772,
"count": 1,
"self": 0.13595947199996772
}
}
}
}
}
}
}