Woako's picture
First Push
d03cd85 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8941027522087097,
"min": 0.8801389932632446,
"max": 2.852539539337158,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8497.552734375,
"min": 8442.29296875,
"max": 29118.72265625,
"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": 11.34383773803711,
"min": 0.17597463726997375,
"max": 11.34383773803711,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2212.04833984375,
"min": 34.13908004760742,
"max": 2304.3701171875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07555392009840481,
"min": 0.06304508007094994,
"max": 0.07555392009840481,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.30221568039361923,
"min": 0.2521803202837998,
"max": 0.3665764667627324,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.15347426092507793,
"min": 0.14331730844010143,
"max": 0.2613505961263881,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6138970437003117,
"min": 0.5732692337604057,
"max": 1.3067529806319405,
"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.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.Environment.CumulativeReward.mean": {
"value": 21.818181818181817,
"min": 3.75,
"max": 22.318181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 960.0,
"min": 165.0,
"max": 1211.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 21.818181818181817,
"min": 3.75,
"max": 22.318181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 960.0,
"min": 165.0,
"max": 1211.0,
"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": "1775405707",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/content/ml-agents/config/ppo/SnowballTarget.yaml --env=/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1775406294"
},
"total": 587.8767594089995,
"count": 1,
"self": 0.5459220479997384,
"children": {
"run_training.setup": {
"total": 0.049356817999978375,
"count": 1,
"self": 0.049356817999978375
},
"TrainerController.start_learning": {
"total": 587.2814805429998,
"count": 1,
"self": 0.6218125020468506,
"children": {
"TrainerController._reset_env": {
"total": 4.099679332000051,
"count": 1,
"self": 4.099679332000051
},
"TrainerController.advance": {
"total": 582.4880712019531,
"count": 18192,
"self": 0.6220457299668851,
"children": {
"env_step": {
"total": 417.29273069399187,
"count": 18192,
"self": 360.75347033100115,
"children": {
"SubprocessEnvManager._take_step": {
"total": 56.14283562002947,
"count": 18192,
"self": 2.009112077984355,
"children": {
"TorchPolicy.evaluate": {
"total": 54.13372354204512,
"count": 18192,
"self": 54.13372354204512
}
}
},
"workers": {
"total": 0.3964247429612442,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 584.3996947319101,
"count": 18192,
"is_parallel": true,
"self": 272.410422848905,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005762674000834522,
"count": 1,
"is_parallel": true,
"self": 0.00409255500017025,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016701190006642719,
"count": 10,
"is_parallel": true,
"self": 0.0016701190006642719
}
}
},
"UnityEnvironment.step": {
"total": 0.04247312600000441,
"count": 1,
"is_parallel": true,
"self": 0.0006978909996178118,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004396580006869044,
"count": 1,
"is_parallel": true,
"self": 0.0004396580006869044
},
"communicator.exchange": {
"total": 0.03916370699971594,
"count": 1,
"is_parallel": true,
"self": 0.03916370699971594
},
"steps_from_proto": {
"total": 0.0021718699999837554,
"count": 1,
"is_parallel": true,
"self": 0.0004259249999449821,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017459450000387733,
"count": 10,
"is_parallel": true,
"self": 0.0017459450000387733
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 311.98927188300513,
"count": 18191,
"is_parallel": true,
"self": 14.076990562035462,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.474230667002303,
"count": 18191,
"is_parallel": true,
"self": 7.474230667002303
},
"communicator.exchange": {
"total": 241.86781987103132,
"count": 18191,
"is_parallel": true,
"self": 241.86781987103132
},
"steps_from_proto": {
"total": 48.57023078293605,
"count": 18191,
"is_parallel": true,
"self": 8.526099449833055,
"children": {
"_process_rank_one_or_two_observation": {
"total": 40.044131333102996,
"count": 181910,
"is_parallel": true,
"self": 40.044131333102996
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 164.5732947779943,
"count": 18192,
"self": 0.8031592430070305,
"children": {
"process_trajectory": {
"total": 31.141210879990467,
"count": 18192,
"self": 30.74365595698964,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3975549230008255,
"count": 4,
"self": 0.3975549230008255
}
}
},
"_update_policy": {
"total": 132.6289246549968,
"count": 90,
"self": 48.457846502968096,
"children": {
"TorchPPOOptimizer.update": {
"total": 84.17107815202871,
"count": 4587,
"self": 84.17107815202871
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.96999915514607e-07,
"count": 1,
"self": 9.96999915514607e-07
},
"TrainerController._save_models": {
"total": 0.07191650999993726,
"count": 1,
"self": 0.0011675910000121803,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07074891899992508,
"count": 1,
"self": 0.07074891899992508
}
}
}
}
}
}
}