c-wang's picture
First
a3cf937
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.666730523109436,
"min": 0.666730523109436,
"max": 0.9866729378700256,
"count": 15
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6857.3232421875,
"min": 6566.41064453125,
"max": 10093.6640625,
"count": 15
},
"SnowballTarget.Step.mean": {
"value": 299968.0,
"min": 159936.0,
"max": 299968.0,
"count": 15
},
"SnowballTarget.Step.sum": {
"value": 299968.0,
"min": 159936.0,
"max": 299968.0,
"count": 15
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.185312271118164,
"min": 12.258326530456543,
"max": 13.198405265808105,
"count": 15
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2689.8037109375,
"min": 2341.34033203125,
"max": 2693.637451171875,
"count": 15
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 15
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 15
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07221462837883783,
"min": 0.061222740285801616,
"max": 0.07271429882019613,
"count": 15
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.36107314189418915,
"min": 0.24489096114320646,
"max": 0.36357149410098066,
"count": 15
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1960777162044656,
"min": 0.19566487579369077,
"max": 0.24073423532878652,
"count": 15
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.980388581022328,
"min": 0.7826595031747631,
"max": 1.1202559412694444,
"count": 15
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 4.712098429333334e-06,
"min": 4.712098429333334e-06,
"max": 0.00014441205186266668,
"count": 15
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 2.356049214666667e-05,
"min": 2.356049214666667e-05,
"max": 0.0006726882757706666,
"count": 15
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10157066666666666,
"min": 0.10157066666666666,
"max": 0.14813733333333334,
"count": 15
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5078533333333333,
"min": 0.4194826666666668,
"max": 0.7242293333333334,
"count": 15
},
"SnowballTarget.Policy.Beta.mean": {
"value": 8.837626666666668e-05,
"min": 8.837626666666668e-05,
"max": 0.0024120529333333334,
"count": 15
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00044188133333333335,
"min": 0.00044188133333333335,
"max": 0.011239043733333336,
"count": 15
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.490909090909092,
"min": 24.545454545454547,
"max": 26.490909090909092,
"count": 15
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1457.0,
"min": 1080.0,
"max": 1457.0,
"count": 15
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.490909090909092,
"min": 24.545454545454547,
"max": 26.490909090909092,
"count": 15
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1457.0,
"min": 1080.0,
"max": 1457.0,
"count": 15
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 15
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 15
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1703288374",
"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 --resume --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": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1703288736"
},
"total": 362.47311773599995,
"count": 1,
"self": 0.6889095609999458,
"children": {
"run_training.setup": {
"total": 0.047931156000004194,
"count": 1,
"self": 0.047931156000004194
},
"TrainerController.start_learning": {
"total": 361.736277019,
"count": 1,
"self": 0.5040170000131639,
"children": {
"TrainerController._reset_env": {
"total": 1.9187489210000876,
"count": 1,
"self": 1.9187489210000876
},
"TrainerController.advance": {
"total": 359.1585240149868,
"count": 13689,
"self": 0.21775044198443538,
"children": {
"env_step": {
"total": 358.9407735730024,
"count": 13689,
"self": 237.7600690699844,
"children": {
"SubprocessEnvManager._take_step": {
"total": 120.95541065500493,
"count": 13689,
"self": 1.1805876149969663,
"children": {
"TorchPolicy.evaluate": {
"total": 119.77482304000796,
"count": 13689,
"self": 119.77482304000796
}
}
},
"workers": {
"total": 0.2252938480130524,
"count": 13689,
"self": 0.0,
"children": {
"worker_root": {
"total": 360.5114726480192,
"count": 13689,
"is_parallel": true,
"self": 177.97682631900489,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020451430000321125,
"count": 1,
"is_parallel": true,
"self": 0.0006058540000140056,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014392890000181069,
"count": 10,
"is_parallel": true,
"self": 0.0014392890000181069
}
}
},
"UnityEnvironment.step": {
"total": 0.042770838000024014,
"count": 1,
"is_parallel": true,
"self": 0.0006391609997535852,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004425870001796284,
"count": 1,
"is_parallel": true,
"self": 0.0004425870001796284
},
"communicator.exchange": {
"total": 0.039587327000162986,
"count": 1,
"is_parallel": true,
"self": 0.039587327000162986
},
"steps_from_proto": {
"total": 0.0021017629999278142,
"count": 1,
"is_parallel": true,
"self": 0.0003894510002737661,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017123119996540481,
"count": 10,
"is_parallel": true,
"self": 0.0017123119996540481
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 182.53464632901432,
"count": 13688,
"is_parallel": true,
"self": 8.344740176002233,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.335751017996699,
"count": 13688,
"is_parallel": true,
"self": 4.335751017996699
},
"communicator.exchange": {
"total": 142.20315469299794,
"count": 13688,
"is_parallel": true,
"self": 142.20315469299794
},
"steps_from_proto": {
"total": 27.651000442017448,
"count": 13688,
"is_parallel": true,
"self": 5.255658572014227,
"children": {
"_process_rank_one_or_two_observation": {
"total": 22.39534187000322,
"count": 136880,
"is_parallel": true,
"self": 22.39534187000322
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00036902800002280856,
"count": 1,
"self": 0.00036902800002280856,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 354.7180364590231,
"count": 509338,
"is_parallel": true,
"self": 11.210605327949906,
"children": {
"process_trajectory": {
"total": 195.4777818420739,
"count": 509338,
"is_parallel": true,
"self": 194.72271360807395,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7550682339999639,
"count": 2,
"is_parallel": true,
"self": 0.7550682339999639
}
}
},
"_update_policy": {
"total": 148.02964928899928,
"count": 68,
"is_parallel": true,
"self": 48.44166850800002,
"children": {
"TorchPPOOptimizer.update": {
"total": 99.58798078099926,
"count": 3465,
"is_parallel": true,
"self": 99.58798078099926
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15461805499990078,
"count": 1,
"self": 0.0025577339999927062,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15206032099990807,
"count": 1,
"self": 0.15206032099990807
}
}
}
}
}
}
}