Lamurias's picture
First Push
fb9bb4d
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8018591403961182,
"min": 0.7911858558654785,
"max": 2.8795294761657715,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7691.4326171875,
"min": 7691.4326171875,
"max": 29520.935546875,
"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": 12.805215835571289,
"min": 0.22351743280887604,
"max": 12.81850528717041,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2497.01708984375,
"min": 43.36238098144531,
"max": 2614.97509765625,
"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": 0.06611996078290937,
"min": 0.06384143450122792,
"max": 0.07360604231636149,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26447984313163747,
"min": 0.2553657380049117,
"max": 0.36547345685882165,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22123715591927368,
"min": 0.09803241439958048,
"max": 0.293126284550218,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8849486236770947,
"min": 0.3921296575983219,
"max": 1.46563142275109,
"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": 24.568181818181817,
"min": 2.6363636363636362,
"max": 25.568181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1081.0,
"min": 116.0,
"max": 1373.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.568181818181817,
"min": 2.6363636363636362,
"max": 25.568181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1081.0,
"min": 116.0,
"max": 1373.0,
"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": "1694793563",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1694794072"
},
"total": 509.65205939,
"count": 1,
"self": 0.48727502099995945,
"children": {
"run_training.setup": {
"total": 0.04674875199998496,
"count": 1,
"self": 0.04674875199998496
},
"TrainerController.start_learning": {
"total": 509.11803561700003,
"count": 1,
"self": 0.6637579630023538,
"children": {
"TrainerController._reset_env": {
"total": 4.461070717999974,
"count": 1,
"self": 4.461070717999974
},
"TrainerController.advance": {
"total": 503.8466288969976,
"count": 18217,
"self": 0.3449262659951273,
"children": {
"env_step": {
"total": 503.50170263100244,
"count": 18217,
"self": 366.6647139830137,
"children": {
"SubprocessEnvManager._take_step": {
"total": 136.49643232299422,
"count": 18217,
"self": 1.9219306279879902,
"children": {
"TorchPolicy.evaluate": {
"total": 134.57450169500623,
"count": 18217,
"self": 134.57450169500623
}
}
},
"workers": {
"total": 0.34055632499450894,
"count": 18217,
"self": 0.0,
"children": {
"worker_root": {
"total": 507.41915126600384,
"count": 18217,
"is_parallel": true,
"self": 236.76022157302236,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00630370299995775,
"count": 1,
"is_parallel": true,
"self": 0.004769011999997019,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015346909999607306,
"count": 10,
"is_parallel": true,
"self": 0.0015346909999607306
}
}
},
"UnityEnvironment.step": {
"total": 0.038869676999979674,
"count": 1,
"is_parallel": true,
"self": 0.0006642619999865929,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003489380000019082,
"count": 1,
"is_parallel": true,
"self": 0.0003489380000019082
},
"communicator.exchange": {
"total": 0.03444207699999424,
"count": 1,
"is_parallel": true,
"self": 0.03444207699999424
},
"steps_from_proto": {
"total": 0.003414399999996931,
"count": 1,
"is_parallel": true,
"self": 0.0014956950000168945,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019187049999800365,
"count": 10,
"is_parallel": true,
"self": 0.0019187049999800365
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 270.6589296929815,
"count": 18216,
"is_parallel": true,
"self": 11.13579221998873,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.739081205998218,
"count": 18216,
"is_parallel": true,
"self": 5.739081205998218
},
"communicator.exchange": {
"total": 215.2248942160029,
"count": 18216,
"is_parallel": true,
"self": 215.2248942160029
},
"steps_from_proto": {
"total": 38.55916205099163,
"count": 18216,
"is_parallel": true,
"self": 7.286227258984923,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.27293479200671,
"count": 182160,
"is_parallel": true,
"self": 31.27293479200671
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014808900004936731,
"count": 1,
"self": 0.00014808900004936731,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 500.0661298909621,
"count": 464716,
"is_parallel": true,
"self": 10.750908652946919,
"children": {
"process_trajectory": {
"total": 275.77746736601557,
"count": 464716,
"is_parallel": true,
"self": 273.83104684201544,
"children": {
"RLTrainer._checkpoint": {
"total": 1.946420524000132,
"count": 4,
"is_parallel": true,
"self": 1.946420524000132
}
}
},
"_update_policy": {
"total": 213.5377538719996,
"count": 90,
"is_parallel": true,
"self": 82.16684165899142,
"children": {
"TorchPPOOptimizer.update": {
"total": 131.37091221300818,
"count": 4587,
"is_parallel": true,
"self": 131.37091221300818
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1464299500000834,
"count": 1,
"self": 0.0009583070002463501,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14547164299983706,
"count": 1,
"self": 0.14547164299983706
}
}
}
}
}
}
}