runpeng's picture
First Push
f17e2b0 verified
Raw
History Blame Contribute Delete
17.6 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7882625460624695,
"min": 0.7882625460624695,
"max": 2.8438127040863037,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7491.64697265625,
"min": 7491.64697265625,
"max": 29029.640625,
"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": 12.986871719360352,
"min": 0.34665751457214355,
"max": 12.986871719360352,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2532.43994140625,
"min": 67.25155639648438,
"max": 2607.77392578125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06850230657387418,
"min": 0.06174229050777606,
"max": 0.07528222347900737,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27400922629549673,
"min": 0.26102281320274023,
"max": 0.3629242520866112,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19802315135066417,
"min": 0.13887928025431784,
"max": 0.27169440119874244,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7920926054026567,
"min": 0.5555171210172714,
"max": 1.3584720059937123,
"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": 25.931818181818183,
"min": 3.909090909090909,
"max": 25.931818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1141.0,
"min": 172.0,
"max": 1421.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.931818181818183,
"min": 3.909090909090909,
"max": 25.931818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1141.0,
"min": 172.0,
"max": 1421.0,
"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": "1780277945",
"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": "1780278453"
},
"total": 507.3338101489999,
"count": 1,
"self": 0.4827183300001252,
"children": {
"run_training.setup": {
"total": 0.02867625799990492,
"count": 1,
"self": 0.02867625799990492
},
"TrainerController.start_learning": {
"total": 506.82241556099984,
"count": 1,
"self": 0.4442868390133299,
"children": {
"TrainerController._reset_env": {
"total": 3.0458333690000927,
"count": 1,
"self": 3.0458333690000927
},
"TrainerController.advance": {
"total": 503.2458276489865,
"count": 18192,
"self": 0.46706175900681046,
"children": {
"env_step": {
"total": 371.99557742400793,
"count": 18192,
"self": 292.30736769398754,
"children": {
"SubprocessEnvManager._take_step": {
"total": 79.42527648301234,
"count": 18192,
"self": 1.4392876700226225,
"children": {
"TorchPolicy.evaluate": {
"total": 77.98598881298972,
"count": 18192,
"self": 77.98598881298972
}
}
},
"workers": {
"total": 0.2629332470080499,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 504.58053109398566,
"count": 18192,
"is_parallel": true,
"self": 248.58256418896622,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005084998000029373,
"count": 1,
"is_parallel": true,
"self": 0.0035993960000269,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014856020000024728,
"count": 10,
"is_parallel": true,
"self": 0.0014856020000024728
}
}
},
"UnityEnvironment.step": {
"total": 0.04112521599995489,
"count": 1,
"is_parallel": true,
"self": 0.0006671659998573887,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047491899999840825,
"count": 1,
"is_parallel": true,
"self": 0.00047491899999840825
},
"communicator.exchange": {
"total": 0.0376323290001892,
"count": 1,
"is_parallel": true,
"self": 0.0376323290001892
},
"steps_from_proto": {
"total": 0.0023508019999098906,
"count": 1,
"is_parallel": true,
"self": 0.00044722599977831123,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019035760001315793,
"count": 10,
"is_parallel": true,
"self": 0.0019035760001315793
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 255.99796690501944,
"count": 18191,
"is_parallel": true,
"self": 11.493549030009262,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.290892244998076,
"count": 18191,
"is_parallel": true,
"self": 6.290892244998076
},
"communicator.exchange": {
"total": 196.05181884200442,
"count": 18191,
"is_parallel": true,
"self": 196.05181884200442
},
"steps_from_proto": {
"total": 42.16170678800768,
"count": 18191,
"is_parallel": true,
"self": 7.360548833923758,
"children": {
"_process_rank_one_or_two_observation": {
"total": 34.80115795408392,
"count": 181910,
"is_parallel": true,
"self": 34.80115795408392
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 130.78318846597176,
"count": 18192,
"self": 0.5939730399932159,
"children": {
"process_trajectory": {
"total": 29.040632848980295,
"count": 18192,
"self": 28.53658630198038,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5040465469999162,
"count": 4,
"self": 0.5040465469999162
}
}
},
"_update_policy": {
"total": 101.14858257699825,
"count": 90,
"self": 41.878783602003296,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.269798974994956,
"count": 4587,
"self": 59.269798974994956
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.02400008472614e-06,
"count": 1,
"self": 1.02400008472614e-06
},
"TrainerController._save_models": {
"total": 0.08646667999983038,
"count": 1,
"self": 0.0008121709997794824,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0856545090000509,
"count": 1,
"self": 0.0856545090000509
}
}
}
}
}
}
}