yuval6967's picture
First Push
d223613
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9947584271430969,
"min": 0.9947584271430969,
"max": 2.8710029125213623,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9530.7802734375,
"min": 9530.7802734375,
"max": 29465.103515625,
"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": 13.03036880493164,
"min": 0.29372358322143555,
"max": 13.03036880493164,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2540.921875,
"min": 56.98237228393555,
"max": 2636.92041015625,
"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": 0.07210913571565042,
"min": 0.05763247565311544,
"max": 0.0741645946534346,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2884365428626017,
"min": 0.23052990261246176,
"max": 0.36249599722784703,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21899401564516274,
"min": 0.10392601340073251,
"max": 0.2785406210843254,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.875976062580651,
"min": 0.41570405360293006,
"max": 1.3927031054216272,
"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": 25.59090909090909,
"min": 2.9318181818181817,
"max": 25.654545454545456,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1126.0,
"min": 129.0,
"max": 1411.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.59090909090909,
"min": 2.9318181818181817,
"max": 25.654545454545456,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1126.0,
"min": 129.0,
"max": 1411.0,
"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": "1685012523",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1685012983"
},
"total": 460.454156257,
"count": 1,
"self": 0.4343446939999467,
"children": {
"run_training.setup": {
"total": 0.040026236000130666,
"count": 1,
"self": 0.040026236000130666
},
"TrainerController.start_learning": {
"total": 459.97978532699995,
"count": 1,
"self": 0.5132354190079695,
"children": {
"TrainerController._reset_env": {
"total": 4.768235554999819,
"count": 1,
"self": 4.768235554999819
},
"TrainerController.advance": {
"total": 454.5685472409921,
"count": 18206,
"self": 0.2562177559866541,
"children": {
"env_step": {
"total": 454.3123294850054,
"count": 18206,
"self": 336.5155976849876,
"children": {
"SubprocessEnvManager._take_step": {
"total": 117.52921939601129,
"count": 18206,
"self": 1.6849619789807093,
"children": {
"TorchPolicy.evaluate": {
"total": 115.84425741703058,
"count": 18206,
"self": 115.84425741703058
}
}
},
"workers": {
"total": 0.2675124040065384,
"count": 18206,
"self": 0.0,
"children": {
"worker_root": {
"total": 458.42866438898864,
"count": 18206,
"is_parallel": true,
"self": 216.38280935899525,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005331423000143332,
"count": 1,
"is_parallel": true,
"self": 0.0038891830001830385,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001442239999960293,
"count": 10,
"is_parallel": true,
"self": 0.001442239999960293
}
}
},
"UnityEnvironment.step": {
"total": 0.0871417549999478,
"count": 1,
"is_parallel": true,
"self": 0.0005634720000671223,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003793549999500101,
"count": 1,
"is_parallel": true,
"self": 0.0003793549999500101
},
"communicator.exchange": {
"total": 0.0842314849999184,
"count": 1,
"is_parallel": true,
"self": 0.0842314849999184
},
"steps_from_proto": {
"total": 0.001967443000012281,
"count": 1,
"is_parallel": true,
"self": 0.00037612599999192753,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015913170000203536,
"count": 10,
"is_parallel": true,
"self": 0.0015913170000203536
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 242.0458550299934,
"count": 18205,
"is_parallel": true,
"self": 9.604126774960605,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.215203273992074,
"count": 18205,
"is_parallel": true,
"self": 5.215203273992074
},
"communicator.exchange": {
"total": 194.99156144802942,
"count": 18205,
"is_parallel": true,
"self": 194.99156144802942
},
"steps_from_proto": {
"total": 32.234963533011296,
"count": 18205,
"is_parallel": true,
"self": 6.1580734860190205,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.076890046992276,
"count": 182050,
"is_parallel": true,
"self": 26.076890046992276
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011381400008758646,
"count": 1,
"self": 0.00011381400008758646,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 451.1328902399473,
"count": 436826,
"is_parallel": true,
"self": 9.449708701938107,
"children": {
"process_trajectory": {
"total": 246.46044051700778,
"count": 436826,
"is_parallel": true,
"self": 245.23333134900804,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2271091679997426,
"count": 4,
"is_parallel": true,
"self": 1.2271091679997426
}
}
},
"_update_policy": {
"total": 195.2227410210014,
"count": 90,
"is_parallel": true,
"self": 77.88251640699673,
"children": {
"TorchPPOOptimizer.update": {
"total": 117.34022461400468,
"count": 4587,
"is_parallel": true,
"self": 117.34022461400468
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1296532979999938,
"count": 1,
"self": 0.0008247949999713455,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12882850300002247,
"count": 1,
"self": 0.12882850300002247
}
}
}
}
}
}
}