PabloTa's picture
First Push
6a90ef5
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9691246747970581,
"min": 0.9691246747970581,
"max": 2.8709192276000977,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9285.18359375,
"min": 9285.18359375,
"max": 29432.6640625,
"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": 12.198149681091309,
"min": 0.48843738436698914,
"max": 12.198149681091309,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2378.63916015625,
"min": 94.75685119628906,
"max": 2466.9794921875,
"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": 0.07036596085469914,
"min": 0.06104878950852664,
"max": 0.0784627340224902,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28146384341879654,
"min": 0.24419515803410655,
"max": 0.36569484045407186,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22328397631645203,
"min": 0.13570349142480387,
"max": 0.29342855593445255,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8931359052658081,
"min": 0.5428139656992155,
"max": 1.4072799976075105,
"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": 24.113636363636363,
"min": 3.6363636363636362,
"max": 24.163636363636364,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1061.0,
"min": 160.0,
"max": 1329.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.113636363636363,
"min": 3.6363636363636362,
"max": 24.163636363636364,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1061.0,
"min": 160.0,
"max": 1329.0,
"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": "1680698132",
"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": "1680698589"
},
"total": 456.17911453700003,
"count": 1,
"self": 0.48665749700001015,
"children": {
"run_training.setup": {
"total": 0.11930386900007761,
"count": 1,
"self": 0.11930386900007761
},
"TrainerController.start_learning": {
"total": 455.57315317099994,
"count": 1,
"self": 0.5628275550041053,
"children": {
"TrainerController._reset_env": {
"total": 5.045790413000077,
"count": 1,
"self": 5.045790413000077
},
"TrainerController.advance": {
"total": 449.8289523379958,
"count": 18204,
"self": 0.2764130720001958,
"children": {
"env_step": {
"total": 449.5525392659956,
"count": 18204,
"self": 329.3828913509874,
"children": {
"SubprocessEnvManager._take_step": {
"total": 119.8970125570097,
"count": 18204,
"self": 1.7110619390148258,
"children": {
"TorchPolicy.evaluate": {
"total": 118.18595061799488,
"count": 18204,
"self": 118.18595061799488
}
}
},
"workers": {
"total": 0.27263535799852434,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 454.19345783800486,
"count": 18204,
"is_parallel": true,
"self": 211.39808138300532,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005570159000058084,
"count": 1,
"is_parallel": true,
"self": 0.0040984290000096735,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014717300000484101,
"count": 10,
"is_parallel": true,
"self": 0.0014717300000484101
}
}
},
"UnityEnvironment.step": {
"total": 0.06529597100006868,
"count": 1,
"is_parallel": true,
"self": 0.0006143460000203049,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00045113500004845264,
"count": 1,
"is_parallel": true,
"self": 0.00045113500004845264
},
"communicator.exchange": {
"total": 0.062404976000038914,
"count": 1,
"is_parallel": true,
"self": 0.062404976000038914
},
"steps_from_proto": {
"total": 0.0018255139999610037,
"count": 1,
"is_parallel": true,
"self": 0.00041499000008116127,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014105239998798424,
"count": 10,
"is_parallel": true,
"self": 0.0014105239998798424
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 242.79537645499954,
"count": 18203,
"is_parallel": true,
"self": 9.925168569004654,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.2675469579988885,
"count": 18203,
"is_parallel": true,
"self": 5.2675469579988885
},
"communicator.exchange": {
"total": 196.30814406199306,
"count": 18203,
"is_parallel": true,
"self": 196.30814406199306
},
"steps_from_proto": {
"total": 31.294516866002937,
"count": 18203,
"is_parallel": true,
"self": 6.1838144609752135,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.110702405027723,
"count": 182030,
"is_parallel": true,
"self": 25.110702405027723
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013133899994954845,
"count": 1,
"self": 0.00013133899994954845,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 446.579039022977,
"count": 404711,
"is_parallel": true,
"self": 9.599212120035872,
"children": {
"process_trajectory": {
"total": 244.41772501794082,
"count": 404711,
"is_parallel": true,
"self": 243.66838590294094,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7493391149998843,
"count": 4,
"is_parallel": true,
"self": 0.7493391149998843
}
}
},
"_update_policy": {
"total": 192.5621018850003,
"count": 90,
"is_parallel": true,
"self": 74.72119648199919,
"children": {
"TorchPPOOptimizer.update": {
"total": 117.8409054030011,
"count": 4584,
"is_parallel": true,
"self": 117.8409054030011
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1354515259999971,
"count": 1,
"self": 0.0009415780000381346,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13450994799995897,
"count": 1,
"self": 0.13450994799995897
}
}
}
}
}
}
}