zayddawood's picture
First Push
9a4b1bb verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8502246737480164,
"min": 0.8502246737480164,
"max": 2.8640687465667725,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8080.53515625,
"min": 8080.53515625,
"max": 29236.4140625,
"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": 13.34539794921875,
"min": 0.5127673149108887,
"max": 13.34539794921875,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2602.3525390625,
"min": 99.47686004638672,
"max": 2700.09912109375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06628675978301508,
"min": 0.0626785148570871,
"max": 0.07492824191611042,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26514703913206034,
"min": 0.2507140594283484,
"max": 0.3746412095805521,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19564151208774716,
"min": 0.10427569699423461,
"max": 0.2992239485622621,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7825660483509886,
"min": 0.41710278797693845,
"max": 1.4565663270506204,
"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": 26.022727272727273,
"min": 3.0681818181818183,
"max": 26.236363636363638,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1145.0,
"min": 135.0,
"max": 1443.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.022727272727273,
"min": 3.0681818181818183,
"max": 26.236363636363638,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1145.0,
"min": 135.0,
"max": 1443.0,
"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": "1770733073",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.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": "1770733494"
},
"total": 421.00551066,
"count": 1,
"self": 0.43400631900021835,
"children": {
"run_training.setup": {
"total": 0.03335296999989623,
"count": 1,
"self": 0.03335296999989623
},
"TrainerController.start_learning": {
"total": 420.5381513709999,
"count": 1,
"self": 0.3536359209904276,
"children": {
"TrainerController._reset_env": {
"total": 3.1120246209998186,
"count": 1,
"self": 3.1120246209998186
},
"TrainerController.advance": {
"total": 416.9976022450096,
"count": 18192,
"self": 0.3672626429890897,
"children": {
"env_step": {
"total": 300.450614122012,
"count": 18192,
"self": 235.88639994301707,
"children": {
"SubprocessEnvManager._take_step": {
"total": 64.36484235000216,
"count": 18192,
"self": 1.173455300990554,
"children": {
"TorchPolicy.evaluate": {
"total": 63.19138704901161,
"count": 18192,
"self": 63.19138704901161
}
}
},
"workers": {
"total": 0.19937182899275285,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 418.79264667499433,
"count": 18192,
"is_parallel": true,
"self": 211.17866079400847,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006644551999897885,
"count": 1,
"is_parallel": true,
"self": 0.003791086000546784,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0028534659993511013,
"count": 10,
"is_parallel": true,
"self": 0.0028534659993511013
}
}
},
"UnityEnvironment.step": {
"total": 0.034451578000016525,
"count": 1,
"is_parallel": true,
"self": 0.0006022150000717374,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039413100012097857,
"count": 1,
"is_parallel": true,
"self": 0.00039413100012097857
},
"communicator.exchange": {
"total": 0.03150760799985619,
"count": 1,
"is_parallel": true,
"self": 0.03150760799985619
},
"steps_from_proto": {
"total": 0.0019476239999676181,
"count": 1,
"is_parallel": true,
"self": 0.000366566000820967,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015810579991466511,
"count": 10,
"is_parallel": true,
"self": 0.0015810579991466511
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 207.61398588098587,
"count": 18191,
"is_parallel": true,
"self": 9.983652436024613,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.2107470810053655,
"count": 18191,
"is_parallel": true,
"self": 5.2107470810053655
},
"communicator.exchange": {
"total": 158.09551443797864,
"count": 18191,
"is_parallel": true,
"self": 158.09551443797864
},
"steps_from_proto": {
"total": 34.32407192597725,
"count": 18191,
"is_parallel": true,
"self": 6.273567828967089,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.050504097010162,
"count": 181910,
"is_parallel": true,
"self": 28.050504097010162
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 116.17972548000853,
"count": 18192,
"self": 0.41221460199244575,
"children": {
"process_trajectory": {
"total": 25.1297945700162,
"count": 18192,
"self": 24.666163092016177,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4636314780000248,
"count": 4,
"self": 0.4636314780000248
}
}
},
"_update_policy": {
"total": 90.63771630799988,
"count": 90,
"self": 37.45608903500465,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.18162727299523,
"count": 4587,
"self": 53.18162727299523
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.859999525157036e-07,
"count": 1,
"self": 8.859999525157036e-07
},
"TrainerController._save_models": {
"total": 0.07488769800011141,
"count": 1,
"self": 0.0007020260002263967,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07418567199988502,
"count": 1,
"self": 0.07418567199988502
}
}
}
}
}
}
}