APLunch's picture
First Push
120de1e verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7050622701644897,
"min": 0.7050622701644897,
"max": 2.8619587421417236,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6817.2470703125,
"min": 6817.2470703125,
"max": 29309.318359375,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.77859878540039,
"min": 0.38366881012916565,
"max": 13.784880638122559,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2824.61279296875,
"min": 74.43174743652344,
"max": 2824.61279296875,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0697863629494118,
"min": 0.06103006867953238,
"max": 0.07554256657552767,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.34893181474705903,
"min": 0.2493930504492977,
"max": 0.37771283287763835,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.16576103445361642,
"min": 0.10228879785612591,
"max": 0.2810851101781808,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8288051722680821,
"min": 0.40915519142450363,
"max": 1.405425550890904,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.0528989824000028e-06,
"min": 3.0528989824000028e-06,
"max": 0.00029675280108239997,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.5264494912000015e-05,
"min": 1.5264494912000015e-05,
"max": 0.001454064015312,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10101760000000001,
"min": 0.10101760000000001,
"max": 0.19891759999999997,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5050880000000001,
"min": 0.41199040000000003,
"max": 0.984688,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 6.0778240000000044e-05,
"min": 6.0778240000000044e-05,
"max": 0.00494598824,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0003038912000000002,
"min": 0.0003038912000000002,
"max": 0.0242359312,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.09090909090909,
"min": 3.022727272727273,
"max": 27.22222222222222,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1490.0,
"min": 133.0,
"max": 1490.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.09090909090909,
"min": 3.022727272727273,
"max": 27.22222222222222,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1490.0,
"min": 133.0,
"max": 1490.0,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1713755893",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 --resume",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1713756922"
},
"total": 1029.065024473,
"count": 1,
"self": 0.4303295839999919,
"children": {
"run_training.setup": {
"total": 0.0499855060002119,
"count": 1,
"self": 0.0499855060002119
},
"TrainerController.start_learning": {
"total": 1028.5847093829998,
"count": 1,
"self": 1.2475098059903758,
"children": {
"TrainerController._reset_env": {
"total": 1.8984900469999957,
"count": 1,
"self": 1.8984900469999957
},
"TrainerController.advance": {
"total": 1025.3477508910096,
"count": 45474,
"self": 0.5957604879963583,
"children": {
"env_step": {
"total": 1024.7519904030132,
"count": 45474,
"self": 655.1423231740359,
"children": {
"SubprocessEnvManager._take_step": {
"total": 368.9562461170117,
"count": 45474,
"self": 3.3754614180870703,
"children": {
"TorchPolicy.evaluate": {
"total": 365.5807846989246,
"count": 45474,
"self": 365.5807846989246
}
}
},
"workers": {
"total": 0.6534211119655993,
"count": 45474,
"self": 0.0,
"children": {
"worker_root": {
"total": 1026.0563821750065,
"count": 45474,
"is_parallel": true,
"self": 513.3324466010185,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002136040000095818,
"count": 1,
"is_parallel": true,
"self": 0.0006323219995465479,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00150371800054927,
"count": 10,
"is_parallel": true,
"self": 0.00150371800054927
}
}
},
"UnityEnvironment.step": {
"total": 0.06122114300023895,
"count": 1,
"is_parallel": true,
"self": 0.0007813479996912065,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038281300021481,
"count": 1,
"is_parallel": true,
"self": 0.00038281300021481
},
"communicator.exchange": {
"total": 0.057974640000338695,
"count": 1,
"is_parallel": true,
"self": 0.057974640000338695
},
"steps_from_proto": {
"total": 0.0020823419999942416,
"count": 1,
"is_parallel": true,
"self": 0.0005318999992596218,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015504420007346198,
"count": 10,
"is_parallel": true,
"self": 0.0015504420007346198
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 512.723935573988,
"count": 45473,
"is_parallel": true,
"self": 24.294358876990373,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 12.698900528976083,
"count": 45473,
"is_parallel": true,
"self": 12.698900528976083
},
"communicator.exchange": {
"total": 397.27121901300734,
"count": 45473,
"is_parallel": true,
"self": 397.27121901300734
},
"steps_from_proto": {
"total": 78.4594571550142,
"count": 45473,
"is_parallel": true,
"self": 14.235531979853477,
"children": {
"_process_rank_one_or_two_observation": {
"total": 64.22392517516073,
"count": 454730,
"is_parallel": true,
"self": 64.22392517516073
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015396199978567893,
"count": 1,
"self": 0.00015396199978567893,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1012.3589760440541,
"count": 1594238,
"is_parallel": true,
"self": 32.25760287538969,
"children": {
"process_trajectory": {
"total": 557.6758756986669,
"count": 1594238,
"is_parallel": true,
"self": 556.4826696096661,
"children": {
"RLTrainer._checkpoint": {
"total": 1.193206089000796,
"count": 10,
"is_parallel": true,
"self": 1.193206089000796
}
}
},
"_update_policy": {
"total": 422.4254974699975,
"count": 227,
"is_parallel": true,
"self": 119.07021200201507,
"children": {
"TorchPPOOptimizer.update": {
"total": 303.3552854679824,
"count": 11574,
"is_parallel": true,
"self": 303.3552854679824
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09080467700005102,
"count": 1,
"self": 0.0011834860001727066,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08962119099987831,
"count": 1,
"self": 0.08962119099987831
}
}
}
}
}
}
}