zhijian12345's picture
First Push
26612c9
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0158671140670776,
"min": 1.0158671140670776,
"max": 2.87337327003479,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9733.0224609375,
"min": 9733.0224609375,
"max": 29426.216796875,
"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": 12.77889633178711,
"min": 0.2949737012386322,
"max": 12.77889633178711,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2491.884765625,
"min": 57.22489929199219,
"max": 2567.6630859375,
"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": 0.0678597593836386,
"min": 0.06328455411455841,
"max": 0.07591126069176016,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2714390375345544,
"min": 0.25857799179057644,
"max": 0.36610823315783697,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19000331787209884,
"min": 0.09457819639047718,
"max": 0.2730994552958245,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7600132714883954,
"min": 0.3783127855619087,
"max": 1.3654972764791227,
"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": 25.204545454545453,
"min": 3.022727272727273,
"max": 25.40909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1109.0,
"min": 133.0,
"max": 1375.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.204545454545453,
"min": 3.022727272727273,
"max": 25.40909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1109.0,
"min": 133.0,
"max": 1375.0,
"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": "1700897056",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1700897736"
},
"total": 680.6769277019998,
"count": 1,
"self": 0.5419930659995771,
"children": {
"run_training.setup": {
"total": 0.06925497300017014,
"count": 1,
"self": 0.06925497300017014
},
"TrainerController.start_learning": {
"total": 680.0656796630001,
"count": 1,
"self": 0.921753874985825,
"children": {
"TrainerController._reset_env": {
"total": 2.904615509999985,
"count": 1,
"self": 2.904615509999985
},
"TrainerController.advance": {
"total": 676.1432947500143,
"count": 18202,
"self": 0.4768629400014106,
"children": {
"env_step": {
"total": 675.6664318100129,
"count": 18202,
"self": 532.3930130890105,
"children": {
"SubprocessEnvManager._take_step": {
"total": 142.83257179099178,
"count": 18202,
"self": 2.7994146349999482,
"children": {
"TorchPolicy.evaluate": {
"total": 140.03315715599183,
"count": 18202,
"self": 140.03315715599183
}
}
},
"workers": {
"total": 0.4408469300105935,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 677.2433092539952,
"count": 18202,
"is_parallel": true,
"self": 310.07624092999845,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00817210300010629,
"count": 1,
"is_parallel": true,
"self": 0.0059634550000282616,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022086480000780284,
"count": 10,
"is_parallel": true,
"self": 0.0022086480000780284
}
}
},
"UnityEnvironment.step": {
"total": 0.05553127600001062,
"count": 1,
"is_parallel": true,
"self": 0.000817686000118556,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004205139998703089,
"count": 1,
"is_parallel": true,
"self": 0.0004205139998703089
},
"communicator.exchange": {
"total": 0.051801940999894214,
"count": 1,
"is_parallel": true,
"self": 0.051801940999894214
},
"steps_from_proto": {
"total": 0.0024911350001275423,
"count": 1,
"is_parallel": true,
"self": 0.0005076519996691786,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019834830004583637,
"count": 10,
"is_parallel": true,
"self": 0.0019834830004583637
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 367.1670683239968,
"count": 18201,
"is_parallel": true,
"self": 15.682330072985451,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.815477995006859,
"count": 18201,
"is_parallel": true,
"self": 7.815477995006859
},
"communicator.exchange": {
"total": 292.4225899590085,
"count": 18201,
"is_parallel": true,
"self": 292.4225899590085
},
"steps_from_proto": {
"total": 51.246670296995944,
"count": 18201,
"is_parallel": true,
"self": 10.776559346054,
"children": {
"_process_rank_one_or_two_observation": {
"total": 40.470110950941944,
"count": 182010,
"is_parallel": true,
"self": 40.470110950941944
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001582840000082797,
"count": 1,
"self": 0.0001582840000082797,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 669.4439397650092,
"count": 717764,
"is_parallel": true,
"self": 18.06206648207649,
"children": {
"process_trajectory": {
"total": 362.6863917319324,
"count": 717764,
"is_parallel": true,
"self": 361.3020973299326,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3842944019997958,
"count": 4,
"is_parallel": true,
"self": 1.3842944019997958
}
}
},
"_update_policy": {
"total": 288.6954815510003,
"count": 90,
"is_parallel": true,
"self": 89.36968581900419,
"children": {
"TorchPPOOptimizer.update": {
"total": 199.3257957319961,
"count": 4587,
"is_parallel": true,
"self": 199.3257957319961
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09585724399994433,
"count": 1,
"self": 0.001312285999802043,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09454495800014229,
"count": 1,
"self": 0.09454495800014229
}
}
}
}
}
}
}