ambi's picture
First Push
b799ff4
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9062235355377197,
"min": 0.9062235355377197,
"max": 2.8618900775909424,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8652.6220703125,
"min": 8652.6220703125,
"max": 29308.6171875,
"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": 12.468184471130371,
"min": 0.22861357033252716,
"max": 12.468184471130371,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2431.2958984375,
"min": 44.35103225708008,
"max": 2497.611328125,
"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": 0.07148958985121948,
"min": 0.06113112486828137,
"max": 0.0749703919511875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2859583594048779,
"min": 0.2547456203439437,
"max": 0.3618487603688503,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22279964058714752,
"min": 0.11110243276583359,
"max": 0.2910040099246829,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8911985623485901,
"min": 0.44440973106333437,
"max": 1.4550200496234145,
"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": 24.90909090909091,
"min": 3.0,
"max": 24.90909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1096.0,
"min": 132.0,
"max": 1348.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.90909090909091,
"min": 3.0,
"max": 24.90909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1096.0,
"min": 132.0,
"max": 1348.0,
"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": "1702485162",
"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",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1702485618"
},
"total": 456.37469968999994,
"count": 1,
"self": 0.435144469999841,
"children": {
"run_training.setup": {
"total": 0.055748073000131626,
"count": 1,
"self": 0.055748073000131626
},
"TrainerController.start_learning": {
"total": 455.88380714699997,
"count": 1,
"self": 0.501438208018044,
"children": {
"TrainerController._reset_env": {
"total": 3.4492166510001425,
"count": 1,
"self": 3.4492166510001425
},
"TrainerController.advance": {
"total": 451.846511276982,
"count": 18200,
"self": 0.24281752499155118,
"children": {
"env_step": {
"total": 451.6036937519905,
"count": 18200,
"self": 304.60266358600575,
"children": {
"SubprocessEnvManager._take_step": {
"total": 146.73562398499803,
"count": 18200,
"self": 1.412584029016898,
"children": {
"TorchPolicy.evaluate": {
"total": 145.32303995598113,
"count": 18200,
"self": 145.32303995598113
}
}
},
"workers": {
"total": 0.26540618098670166,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 454.73734472001115,
"count": 18200,
"is_parallel": true,
"self": 225.03391809104346,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00504031299988128,
"count": 1,
"is_parallel": true,
"self": 0.003514404999805265,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001525908000076015,
"count": 10,
"is_parallel": true,
"self": 0.001525908000076015
}
}
},
"UnityEnvironment.step": {
"total": 0.03436186900012217,
"count": 1,
"is_parallel": true,
"self": 0.0005976350003038533,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004126100000121369,
"count": 1,
"is_parallel": true,
"self": 0.0004126100000121369
},
"communicator.exchange": {
"total": 0.03139612799986935,
"count": 1,
"is_parallel": true,
"self": 0.03139612799986935
},
"steps_from_proto": {
"total": 0.0019554959999368293,
"count": 1,
"is_parallel": true,
"self": 0.00037777800002913864,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015777179999076907,
"count": 10,
"is_parallel": true,
"self": 0.0015777179999076907
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 229.7034266289677,
"count": 18199,
"is_parallel": true,
"self": 10.19973525892101,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.09733404900453,
"count": 18199,
"is_parallel": true,
"self": 5.09733404900453
},
"communicator.exchange": {
"total": 181.89960417003135,
"count": 18199,
"is_parallel": true,
"self": 181.89960417003135
},
"steps_from_proto": {
"total": 32.5067531510108,
"count": 18199,
"is_parallel": true,
"self": 5.915528308993544,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.591224842017255,
"count": 181990,
"is_parallel": true,
"self": 26.591224842017255
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.7745999861726887e-05,
"count": 1,
"self": 3.7745999861726887e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 448.0909873159869,
"count": 478436,
"is_parallel": true,
"self": 10.031094698984134,
"children": {
"process_trajectory": {
"total": 254.61320512200382,
"count": 478436,
"is_parallel": true,
"self": 254.10745712200378,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5057480000000396,
"count": 4,
"is_parallel": true,
"self": 0.5057480000000396
}
}
},
"_update_policy": {
"total": 183.44668749499897,
"count": 90,
"is_parallel": true,
"self": 56.41601057100115,
"children": {
"TorchPPOOptimizer.update": {
"total": 127.03067692399782,
"count": 4587,
"is_parallel": true,
"self": 127.03067692399782
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08660326499989424,
"count": 1,
"self": 0.000872816999844872,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08573044800004936,
"count": 1,
"self": 0.08573044800004936
}
}
}
}
}
}
}