erikbritto's picture
Second Push
2e8b35c verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.828833818435669,
"min": 0.828833818435669,
"max": 2.871260404586792,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7913.70556640625,
"min": 7913.70556640625,
"max": 29404.578125,
"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": 12.951014518737793,
"min": 0.3331141769886017,
"max": 12.951014518737793,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2525.44775390625,
"min": 64.62415313720703,
"max": 2619.09521484375,
"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": 0.06766920992602393,
"min": 0.06245685854656924,
"max": 0.07325196615020818,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27067683970409573,
"min": 0.24982743418627695,
"max": 0.36408767507322515,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.24093393017263973,
"min": 0.09594164458423049,
"max": 0.30282997471444745,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9637357206905589,
"min": 0.38376657833692196,
"max": 1.4248583121042628,
"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": 2.840909090909091,
"max": 25.386363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1117.0,
"min": 125.0,
"max": 1393.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.386363636363637,
"min": 2.840909090909091,
"max": 25.386363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1117.0,
"min": 125.0,
"max": 1393.0,
"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": "1718292357",
"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 --resume",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1718292796"
},
"total": 438.9636839099999,
"count": 1,
"self": 0.5363960929994391,
"children": {
"run_training.setup": {
"total": 0.051544283000112046,
"count": 1,
"self": 0.051544283000112046
},
"TrainerController.start_learning": {
"total": 438.3757435340003,
"count": 1,
"self": 0.5481973360338088,
"children": {
"TrainerController._reset_env": {
"total": 2.529457051999998,
"count": 1,
"self": 2.529457051999998
},
"TrainerController.advance": {
"total": 435.2048031149666,
"count": 18201,
"self": 0.25011170193511134,
"children": {
"env_step": {
"total": 434.95469141303147,
"count": 18201,
"self": 281.55268144201455,
"children": {
"SubprocessEnvManager._take_step": {
"total": 153.13020963399686,
"count": 18201,
"self": 1.436049656997966,
"children": {
"TorchPolicy.evaluate": {
"total": 151.6941599769989,
"count": 18201,
"self": 151.6941599769989
}
}
},
"workers": {
"total": 0.2718003370200677,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 437.2015182150101,
"count": 18201,
"is_parallel": true,
"self": 221.61886098397713,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002250156000172865,
"count": 1,
"is_parallel": true,
"self": 0.0007092860000739165,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015408700000989484,
"count": 10,
"is_parallel": true,
"self": 0.0015408700000989484
}
}
},
"UnityEnvironment.step": {
"total": 0.07770269499997084,
"count": 1,
"is_parallel": true,
"self": 0.0006510920002256171,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00036915599980602565,
"count": 1,
"is_parallel": true,
"self": 0.00036915599980602565
},
"communicator.exchange": {
"total": 0.07480597399990074,
"count": 1,
"is_parallel": true,
"self": 0.07480597399990074
},
"steps_from_proto": {
"total": 0.0018764730000384588,
"count": 1,
"is_parallel": true,
"self": 0.00032428999975309125,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015521830002853676,
"count": 10,
"is_parallel": true,
"self": 0.0015521830002853676
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 215.58265723103295,
"count": 18200,
"is_parallel": true,
"self": 10.001739922033721,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.1493432830134225,
"count": 18200,
"is_parallel": true,
"self": 5.1493432830134225
},
"communicator.exchange": {
"total": 168.19485473599207,
"count": 18200,
"is_parallel": true,
"self": 168.19485473599207
},
"steps_from_proto": {
"total": 32.236719289993744,
"count": 18200,
"is_parallel": true,
"self": 5.9806311390163955,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.256088150977348,
"count": 182000,
"is_parallel": true,
"self": 26.256088150977348
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013325700001587393,
"count": 1,
"self": 0.00013325700001587393,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 429.8701374839518,
"count": 668342,
"is_parallel": true,
"self": 14.026258387136522,
"children": {
"process_trajectory": {
"total": 237.97980312481332,
"count": 668342,
"is_parallel": true,
"self": 237.3390907958128,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6407123290005075,
"count": 4,
"is_parallel": true,
"self": 0.6407123290005075
}
}
},
"_update_policy": {
"total": 177.86407597200196,
"count": 90,
"is_parallel": true,
"self": 55.76588422999703,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.09819174200493,
"count": 4587,
"is_parallel": true,
"self": 122.09819174200493
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09315277399991828,
"count": 1,
"self": 0.0012925870000799478,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09186018699983833,
"count": 1,
"self": 0.09186018699983833
}
}
}
}
}
}
}