VAZaytsev's picture
training
099632f
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.051272988319397,
"min": 1.0170701742172241,
"max": 2.868896961212158,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10118.501953125,
"min": 10118.501953125,
"max": 29380.373046875,
"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": 12.81018352508545,
"min": 0.405639111995697,
"max": 12.81018352508545,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2497.98583984375,
"min": 78.69398498535156,
"max": 2590.296875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0776061617185655,
"min": 0.05710873881174598,
"max": 0.0776061617185655,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.310424646874262,
"min": 0.22843495524698393,
"max": 0.36538541470922525,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20772941483586443,
"min": 0.1339574681718231,
"max": 0.2973157909570956,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8309176593434577,
"min": 0.5358298726872924,
"max": 1.3194364104785172,
"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": 25.568181818181817,
"min": 3.5454545454545454,
"max": 25.568181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1125.0,
"min": 156.0,
"max": 1396.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.568181818181817,
"min": 3.5454545454545454,
"max": 25.568181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1125.0,
"min": 156.0,
"max": 1396.0,
"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": "1678019819",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.22.4",
"end_time_seconds": "1678020298"
},
"total": 478.66905639,
"count": 1,
"self": 0.7381102689999466,
"children": {
"run_training.setup": {
"total": 0.11909876900000427,
"count": 1,
"self": 0.11909876900000427
},
"TrainerController.start_learning": {
"total": 477.81184735200003,
"count": 1,
"self": 0.5789546669935817,
"children": {
"TrainerController._reset_env": {
"total": 9.88233825499998,
"count": 1,
"self": 9.88233825499998
},
"TrainerController.advance": {
"total": 467.1611741310064,
"count": 18219,
"self": 0.2826362190085092,
"children": {
"env_step": {
"total": 466.8785379119979,
"count": 18219,
"self": 324.2312912619899,
"children": {
"SubprocessEnvManager._take_step": {
"total": 142.35295613701027,
"count": 18219,
"self": 1.5714029710130148,
"children": {
"TorchPolicy.evaluate": {
"total": 140.78155316599725,
"count": 18219,
"self": 31.852579622995222,
"children": {
"TorchPolicy.sample_actions": {
"total": 108.92897354300203,
"count": 18219,
"self": 108.92897354300203
}
}
}
}
},
"workers": {
"total": 0.29429051299774756,
"count": 18219,
"self": 0.0,
"children": {
"worker_root": {
"total": 476.14166978599167,
"count": 18219,
"is_parallel": true,
"self": 229.88090772499817,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006295904000012342,
"count": 1,
"is_parallel": true,
"self": 0.005002111000010245,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001293793000002097,
"count": 10,
"is_parallel": true,
"self": 0.001293793000002097
}
}
},
"UnityEnvironment.step": {
"total": 0.0394459789999928,
"count": 1,
"is_parallel": true,
"self": 0.0007145479999621784,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00034325699999726567,
"count": 1,
"is_parallel": true,
"self": 0.00034325699999726567
},
"communicator.exchange": {
"total": 0.036293932000035056,
"count": 1,
"is_parallel": true,
"self": 0.036293932000035056
},
"steps_from_proto": {
"total": 0.002094241999998303,
"count": 1,
"is_parallel": true,
"self": 0.000490292999927533,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016039490000707701,
"count": 10,
"is_parallel": true,
"self": 0.0016039490000707701
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 246.2607620609935,
"count": 18218,
"is_parallel": true,
"self": 9.9284912779936,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.360988206002162,
"count": 18218,
"is_parallel": true,
"self": 5.360988206002162
},
"communicator.exchange": {
"total": 198.92844459200268,
"count": 18218,
"is_parallel": true,
"self": 198.92844459200268
},
"steps_from_proto": {
"total": 32.04283798499506,
"count": 18218,
"is_parallel": true,
"self": 7.090635067996004,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.952202916999056,
"count": 182180,
"is_parallel": true,
"self": 24.952202916999056
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00019136000003072695,
"count": 1,
"self": 0.00019136000003072695,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 463.78587482701107,
"count": 408862,
"is_parallel": true,
"self": 10.26670675705094,
"children": {
"process_trajectory": {
"total": 264.46009117695996,
"count": 408862,
"is_parallel": true,
"self": 263.43942993495995,
"children": {
"RLTrainer._checkpoint": {
"total": 1.020661242000017,
"count": 4,
"is_parallel": true,
"self": 1.020661242000017
}
}
},
"_update_policy": {
"total": 189.05907689300017,
"count": 90,
"is_parallel": true,
"self": 68.96119403100369,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.09788286199648,
"count": 4587,
"is_parallel": true,
"self": 120.09788286199648
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.18918893900001876,
"count": 1,
"self": 0.0012132519999568103,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18797568700006195,
"count": 1,
"self": 0.18797568700006195
}
}
}
}
}
}
}