TikhonRadkevich's picture
First Push
cedea33 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8818767070770264,
"min": 0.8818767070770264,
"max": 2.8559212684631348,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8429.859375,
"min": 8429.859375,
"max": 29278.904296875,
"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": 12.654909133911133,
"min": 0.26328936219215393,
"max": 12.654909133911133,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2467.707275390625,
"min": 51.0781364440918,
"max": 2560.200927734375,
"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": 0.07109027362193777,
"min": 0.06339106864071059,
"max": 0.07469807950031941,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2843610944877511,
"min": 0.25356427456284236,
"max": 0.36655295753449785,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20034525985373003,
"min": 0.09612059001194533,
"max": 0.27373821675485255,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8013810394149201,
"min": 0.3844823600477813,
"max": 1.3422563578568252,
"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": 25.227272727272727,
"min": 2.590909090909091,
"max": 25.227272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1110.0,
"min": 114.0,
"max": 1369.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.227272727272727,
"min": 2.590909090909091,
"max": 25.227272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1110.0,
"min": 114.0,
"max": 1369.0,
"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": "1710245673",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/tikhon/anaconda3/envs/mlagents/bin/mlagents-learn ../config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --results-dir=./logs/snowball/ --torch-device=cpu --force --width=1080 --height=720 --no-graphics",
"mlagents_version": "1.0.0",
"mlagents_envs_version": "1.0.0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1",
"numpy_version": "1.21.2",
"end_time_seconds": "1710245953"
},
"total": 280.6193071330001,
"count": 1,
"self": 0.26885454600005687,
"children": {
"run_training.setup": {
"total": 0.0188365840001552,
"count": 1,
"self": 0.0188365840001552
},
"TrainerController.start_learning": {
"total": 280.3316160029999,
"count": 1,
"self": 0.38957348599274155,
"children": {
"TrainerController._reset_env": {
"total": 1.1189038050001727,
"count": 1,
"self": 1.1189038050001727
},
"TrainerController.advance": {
"total": 278.7674921420071,
"count": 18199,
"self": 0.1984509910091674,
"children": {
"env_step": {
"total": 278.5690411509979,
"count": 18199,
"self": 208.4714537270022,
"children": {
"SubprocessEnvManager._take_step": {
"total": 69.88309368598925,
"count": 18199,
"self": 0.9722476039914909,
"children": {
"TorchPolicy.evaluate": {
"total": 68.91084608199776,
"count": 18199,
"self": 68.91084608199776
}
}
},
"workers": {
"total": 0.21449373800646754,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 279.8432338469861,
"count": 18199,
"is_parallel": true,
"self": 126.30388360600341,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001387552999858599,
"count": 1,
"is_parallel": true,
"self": 0.0003593710000586725,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010281819997999264,
"count": 10,
"is_parallel": true,
"self": 0.0010281819997999264
}
}
},
"UnityEnvironment.step": {
"total": 0.024325101999920662,
"count": 1,
"is_parallel": true,
"self": 0.0007572279998839804,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00017716900015329884,
"count": 1,
"is_parallel": true,
"self": 0.00017716900015329884
},
"communicator.exchange": {
"total": 0.022194660999957705,
"count": 1,
"is_parallel": true,
"self": 0.022194660999957705
},
"steps_from_proto": {
"total": 0.0011960439999256778,
"count": 1,
"is_parallel": true,
"self": 0.0002497820000826323,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009462619998430455,
"count": 10,
"is_parallel": true,
"self": 0.0009462619998430455
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 153.53935024098269,
"count": 18198,
"is_parallel": true,
"self": 7.501505149978584,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.754466746985827,
"count": 18198,
"is_parallel": true,
"self": 3.754466746985827
},
"communicator.exchange": {
"total": 118.39401514000997,
"count": 18198,
"is_parallel": true,
"self": 118.39401514000997
},
"steps_from_proto": {
"total": 23.889363204008305,
"count": 18198,
"is_parallel": true,
"self": 4.1314748880270145,
"children": {
"_process_rank_one_or_two_observation": {
"total": 19.75788831598129,
"count": 181980,
"is_parallel": true,
"self": 19.75788831598129
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.000180125000042608,
"count": 1,
"self": 0.000180125000042608,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 278.0940593040068,
"count": 179838,
"is_parallel": true,
"self": 2.4721494300117683,
"children": {
"process_trajectory": {
"total": 153.6792066159942,
"count": 179838,
"is_parallel": true,
"self": 153.33060423299412,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3486023830000704,
"count": 4,
"is_parallel": true,
"self": 0.3486023830000704
}
}
},
"_update_policy": {
"total": 121.94270325800085,
"count": 90,
"is_parallel": true,
"self": 35.33290451300081,
"children": {
"TorchPPOOptimizer.update": {
"total": 86.60979874500003,
"count": 4587,
"is_parallel": true,
"self": 86.60979874500003
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.055466444999865416,
"count": 1,
"self": 0.0008426150000104826,
"children": {
"RLTrainer._checkpoint": {
"total": 0.054623829999854934,
"count": 1,
"self": 0.054623829999854934
}
}
}
}
}
}
}