slopezay's picture
First training of the SnowballTarget env
4d5838f
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9524672627449036,
"min": 0.9524672627449036,
"max": 2.874685287475586,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9094.1572265625,
"min": 9094.1572265625,
"max": 29439.65234375,
"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": 12.358543395996094,
"min": 0.45242589712142944,
"max": 12.358543395996094,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2409.916015625,
"min": 87.77062225341797,
"max": 2484.14453125,
"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": 0.06574422648997165,
"min": 0.060645651081180335,
"max": 0.07569625275551944,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2629769059598866,
"min": 0.24258260432472134,
"max": 0.37718214893567503,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19242349183004276,
"min": 0.11181013745497728,
"max": 0.29029667092596784,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.769693967320171,
"min": 0.44724054981990913,
"max": 1.3823223327304803,
"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": 24.454545454545453,
"min": 3.272727272727273,
"max": 24.454545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1076.0,
"min": 144.0,
"max": 1342.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.454545454545453,
"min": 3.272727272727273,
"max": 24.454545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1076.0,
"min": 144.0,
"max": 1342.0,
"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": "1678199617",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.22.4",
"end_time_seconds": "1678200078"
},
"total": 460.68354240300005,
"count": 1,
"self": 0.44124394200002826,
"children": {
"run_training.setup": {
"total": 0.11846018000005643,
"count": 1,
"self": 0.11846018000005643
},
"TrainerController.start_learning": {
"total": 460.12383828099996,
"count": 1,
"self": 0.526305405993412,
"children": {
"TrainerController._reset_env": {
"total": 8.748156042000005,
"count": 1,
"self": 8.748156042000005
},
"TrainerController.advance": {
"total": 450.72485629800644,
"count": 18202,
"self": 0.2922708219917922,
"children": {
"env_step": {
"total": 450.43258547601465,
"count": 18202,
"self": 311.8852581660051,
"children": {
"SubprocessEnvManager._take_step": {
"total": 138.27977187600357,
"count": 18202,
"self": 1.4763178580062686,
"children": {
"TorchPolicy.evaluate": {
"total": 136.8034540179973,
"count": 18202,
"self": 30.499199299004545,
"children": {
"TorchPolicy.sample_actions": {
"total": 106.30425471899275,
"count": 18202,
"self": 106.30425471899275
}
}
}
}
},
"workers": {
"total": 0.2675554340059989,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 458.55287154602456,
"count": 18202,
"is_parallel": true,
"self": 221.03327589801506,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0056766269999570795,
"count": 1,
"is_parallel": true,
"self": 0.004330076999963239,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013465499999938402,
"count": 10,
"is_parallel": true,
"self": 0.0013465499999938402
}
}
},
"UnityEnvironment.step": {
"total": 0.04871134400002575,
"count": 1,
"is_parallel": true,
"self": 0.000572463999901629,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003768680001030589,
"count": 1,
"is_parallel": true,
"self": 0.0003768680001030589
},
"communicator.exchange": {
"total": 0.04586413300000913,
"count": 1,
"is_parallel": true,
"self": 0.04586413300000913
},
"steps_from_proto": {
"total": 0.0018978790000119261,
"count": 1,
"is_parallel": true,
"self": 0.0004191840000657976,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014786949999461285,
"count": 10,
"is_parallel": true,
"self": 0.0014786949999461285
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 237.5195956480095,
"count": 18201,
"is_parallel": true,
"self": 9.566932467027414,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.16217278098793,
"count": 18201,
"is_parallel": true,
"self": 5.16217278098793
},
"communicator.exchange": {
"total": 192.16608383699088,
"count": 18201,
"is_parallel": true,
"self": 192.16608383699088
},
"steps_from_proto": {
"total": 30.624406563003276,
"count": 18201,
"is_parallel": true,
"self": 6.650039030984772,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.974367532018505,
"count": 182010,
"is_parallel": true,
"self": 23.974367532018505
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001191070000459149,
"count": 1,
"self": 0.0001191070000459149,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 447.43120328796283,
"count": 400916,
"is_parallel": true,
"self": 9.797428695971917,
"children": {
"process_trajectory": {
"total": 256.00033036999196,
"count": 400916,
"is_parallel": true,
"self": 254.79594997299193,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2043803970000226,
"count": 4,
"is_parallel": true,
"self": 1.2043803970000226
}
}
},
"_update_policy": {
"total": 181.63344422199896,
"count": 90,
"is_parallel": true,
"self": 62.32151819599949,
"children": {
"TorchPPOOptimizer.update": {
"total": 119.31192602599947,
"count": 4587,
"is_parallel": true,
"self": 119.31192602599947
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1244014280000556,
"count": 1,
"self": 0.000870880000093166,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12353054799996244,
"count": 1,
"self": 0.12353054799996244
}
}
}
}
}
}
}