APP0001's picture
First Push
53dfe63 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8014504909515381,
"min": 0.8014504909515381,
"max": 2.8450067043304443,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7616.9853515625,
"min": 7616.9853515625,
"max": 29041.828125,
"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": 13.299307823181152,
"min": 0.24983946979045868,
"max": 13.32953929901123,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2593.364990234375,
"min": 48.46885681152344,
"max": 2719.22607421875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07005754314299088,
"min": 0.06273005179565527,
"max": 0.07362260096501011,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28023017257196353,
"min": 0.2509202071826211,
"max": 0.36811300482505055,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1729726059837084,
"min": 0.10898495934431113,
"max": 0.28200172822849423,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6918904239348336,
"min": 0.4359398373772445,
"max": 1.410008641142471,
"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": 3.0454545454545454,
"max": 26.272727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1145.0,
"min": 134.0,
"max": 1445.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.022727272727273,
"min": 3.0454545454545454,
"max": 26.272727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1145.0,
"min": 134.0,
"max": 1445.0,
"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": "1744455133",
"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 --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1744455547"
},
"total": 414.2450577090001,
"count": 1,
"self": 0.4377081050001834,
"children": {
"run_training.setup": {
"total": 0.020727546999978586,
"count": 1,
"self": 0.020727546999978586
},
"TrainerController.start_learning": {
"total": 413.78662205699993,
"count": 1,
"self": 0.32329187000505044,
"children": {
"TrainerController._reset_env": {
"total": 3.0927125050000086,
"count": 1,
"self": 3.0927125050000086
},
"TrainerController.advance": {
"total": 410.2806258319947,
"count": 18192,
"self": 0.33114816201373287,
"children": {
"env_step": {
"total": 289.0217386579975,
"count": 18192,
"self": 219.515831885961,
"children": {
"SubprocessEnvManager._take_step": {
"total": 69.30968657601375,
"count": 18192,
"self": 1.2086387020094662,
"children": {
"TorchPolicy.evaluate": {
"total": 68.10104787400428,
"count": 18192,
"self": 68.10104787400428
}
}
},
"workers": {
"total": 0.19622019602275032,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 412.32236195901396,
"count": 18192,
"is_parallel": true,
"self": 219.67686585199908,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005533752000019376,
"count": 1,
"is_parallel": true,
"self": 0.003969499999584514,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015642520004348626,
"count": 10,
"is_parallel": true,
"self": 0.0015642520004348626
}
}
},
"UnityEnvironment.step": {
"total": 0.03435929100010071,
"count": 1,
"is_parallel": true,
"self": 0.0005493769999702636,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038751300007788814,
"count": 1,
"is_parallel": true,
"self": 0.00038751300007788814
},
"communicator.exchange": {
"total": 0.03161931300019205,
"count": 1,
"is_parallel": true,
"self": 0.03161931300019205
},
"steps_from_proto": {
"total": 0.0018030879998605087,
"count": 1,
"is_parallel": true,
"self": 0.0003509169998778816,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014521709999826271,
"count": 10,
"is_parallel": true,
"self": 0.0014521709999826271
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 192.64549610701488,
"count": 18191,
"is_parallel": true,
"self": 9.371842954014028,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.36492461700891,
"count": 18191,
"is_parallel": true,
"self": 5.36492461700891
},
"communicator.exchange": {
"total": 147.9550713940066,
"count": 18191,
"is_parallel": true,
"self": 147.9550713940066
},
"steps_from_proto": {
"total": 29.95365714198533,
"count": 18191,
"is_parallel": true,
"self": 5.25280322193521,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.700853920050122,
"count": 181910,
"is_parallel": true,
"self": 24.700853920050122
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 120.92773901198348,
"count": 18192,
"self": 0.40967527699945094,
"children": {
"process_trajectory": {
"total": 26.370434792984042,
"count": 18192,
"self": 25.749916320983857,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6205184720001853,
"count": 4,
"self": 0.6205184720001853
}
}
},
"_update_policy": {
"total": 94.14762894199998,
"count": 90,
"self": 37.6943166050105,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.453312336989484,
"count": 4587,
"self": 56.453312336989484
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.950000847107731e-07,
"count": 1,
"self": 8.950000847107731e-07
},
"TrainerController._save_models": {
"total": 0.0899909550000757,
"count": 1,
"self": 0.0008792979999725503,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08911165700010315,
"count": 1,
"self": 0.08911165700010315
}
}
}
}
}
}
}