Issacwong
First Push
9c28925
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0526694059371948,
"min": 1.0526694059371948,
"max": 2.866462469100952,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10050.8876953125,
"min": 10050.8876953125,
"max": 29355.443359375,
"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": 12.976506233215332,
"min": 0.31622153520584106,
"max": 12.976506233215332,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2530.418701171875,
"min": 61.34697723388672,
"max": 2637.292236328125,
"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": 0.060685898395604454,
"min": 0.06029585279825637,
"max": 0.07559590219570252,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24274359358241782,
"min": 0.24274359358241782,
"max": 0.36149172339983304,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.195021525609727,
"min": 0.10770959159651516,
"max": 0.2932440816041301,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.780086102438908,
"min": 0.43083836638606066,
"max": 1.3926264024248312,
"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": 25.954545454545453,
"min": 3.0681818181818183,
"max": 25.954545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1142.0,
"min": 135.0,
"max": 1402.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.954545454545453,
"min": 3.0681818181818183,
"max": 25.954545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1142.0,
"min": 135.0,
"max": 1402.0,
"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": "1681395732",
"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": "1681396230"
},
"total": 497.986568402,
"count": 1,
"self": 0.38548203100003775,
"children": {
"run_training.setup": {
"total": 0.10493020100000194,
"count": 1,
"self": 0.10493020100000194
},
"TrainerController.start_learning": {
"total": 497.49615616999995,
"count": 1,
"self": 0.638761187997261,
"children": {
"TrainerController._reset_env": {
"total": 4.935698524999964,
"count": 1,
"self": 4.935698524999964
},
"TrainerController.advance": {
"total": 491.77394289100283,
"count": 18200,
"self": 0.30320311800085165,
"children": {
"env_step": {
"total": 491.470739773002,
"count": 18200,
"self": 357.926388778,
"children": {
"SubprocessEnvManager._take_step": {
"total": 133.23467626399957,
"count": 18200,
"self": 1.9476853310043793,
"children": {
"TorchPolicy.evaluate": {
"total": 131.2869909329952,
"count": 18200,
"self": 131.2869909329952
}
}
},
"workers": {
"total": 0.30967473100241705,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 495.7412173009978,
"count": 18200,
"is_parallel": true,
"self": 229.5043622020048,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004837656000006518,
"count": 1,
"is_parallel": true,
"self": 0.0032996350000757957,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015380209999307226,
"count": 10,
"is_parallel": true,
"self": 0.0015380209999307226
}
}
},
"UnityEnvironment.step": {
"total": 0.06718991100001404,
"count": 1,
"is_parallel": true,
"self": 0.0006131279999976869,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004531229999997777,
"count": 1,
"is_parallel": true,
"self": 0.0004531229999997777
},
"communicator.exchange": {
"total": 0.06272163400001318,
"count": 1,
"is_parallel": true,
"self": 0.06272163400001318
},
"steps_from_proto": {
"total": 0.0034020260000033886,
"count": 1,
"is_parallel": true,
"self": 0.0004576130000941703,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0029444129999092183,
"count": 10,
"is_parallel": true,
"self": 0.0029444129999092183
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 266.236855098993,
"count": 18199,
"is_parallel": true,
"self": 10.576023546999522,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.099076834996197,
"count": 18199,
"is_parallel": true,
"self": 6.099076834996197
},
"communicator.exchange": {
"total": 213.81245911599217,
"count": 18199,
"is_parallel": true,
"self": 213.81245911599217
},
"steps_from_proto": {
"total": 35.74929560100509,
"count": 18199,
"is_parallel": true,
"self": 7.202667969975153,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.546627631029935,
"count": 181990,
"is_parallel": true,
"self": 28.546627631029935
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013284499993915233,
"count": 1,
"self": 0.00013284499993915233,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 487.892872681987,
"count": 447156,
"is_parallel": true,
"self": 11.627206424932808,
"children": {
"process_trajectory": {
"total": 272.0869096230543,
"count": 447156,
"is_parallel": true,
"self": 270.6632690520541,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4236405710001918,
"count": 4,
"is_parallel": true,
"self": 1.4236405710001918
}
}
},
"_update_policy": {
"total": 204.1787566339999,
"count": 90,
"is_parallel": true,
"self": 74.19509986600212,
"children": {
"TorchPPOOptimizer.update": {
"total": 129.9836567679978,
"count": 4587,
"is_parallel": true,
"self": 129.9836567679978
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14762072099995294,
"count": 1,
"self": 0.0009127559999342338,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1467079650000187,
"count": 1,
"self": 0.1467079650000187
}
}
}
}
}
}
}