NDani's picture
First Push
9c54992 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9900192618370056,
"min": 0.9900192618370056,
"max": 2.871168851852417,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9452.7041015625,
"min": 9452.7041015625,
"max": 29403.640625,
"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": 12.843034744262695,
"min": 0.41138356924057007,
"max": 12.843034744262695,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2504.391845703125,
"min": 79.80841064453125,
"max": 2607.0390625,
"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": 0.07111859851084221,
"min": 0.061685169718140406,
"max": 0.0725368581761323,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28447439404336883,
"min": 0.24674067887256163,
"max": 0.3626842908806615,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18917143498273456,
"min": 0.10294556243952328,
"max": 0.28508589307174964,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7566857399309382,
"min": 0.41178224975809313,
"max": 1.3263526047561685,
"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": 25.477272727272727,
"min": 3.022727272727273,
"max": 25.477272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1121.0,
"min": 133.0,
"max": 1379.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.477272727272727,
"min": 3.022727272727273,
"max": 25.477272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1121.0,
"min": 133.0,
"max": 1379.0,
"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": "1710246026",
"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",
"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": "1710246452"
},
"total": 426.273322474,
"count": 1,
"self": 0.45919346100026814,
"children": {
"run_training.setup": {
"total": 0.0634816349997891,
"count": 1,
"self": 0.0634816349997891
},
"TrainerController.start_learning": {
"total": 425.75064737799994,
"count": 1,
"self": 0.5275170099901061,
"children": {
"TrainerController._reset_env": {
"total": 3.066936589999841,
"count": 1,
"self": 3.066936589999841
},
"TrainerController.advance": {
"total": 422.0600801190101,
"count": 18199,
"self": 0.25849760300184244,
"children": {
"env_step": {
"total": 421.80158251600824,
"count": 18199,
"self": 269.9786531370023,
"children": {
"SubprocessEnvManager._take_step": {
"total": 151.5625625270045,
"count": 18199,
"self": 1.3793872309972812,
"children": {
"TorchPolicy.evaluate": {
"total": 150.18317529600722,
"count": 18199,
"self": 150.18317529600722
}
}
},
"workers": {
"total": 0.2603668520014253,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 424.7005568079994,
"count": 18199,
"is_parallel": true,
"self": 214.71287985101935,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008086713000011514,
"count": 1,
"is_parallel": true,
"self": 0.006307863000074576,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017788499999369378,
"count": 10,
"is_parallel": true,
"self": 0.0017788499999369378
}
}
},
"UnityEnvironment.step": {
"total": 0.035071547999905306,
"count": 1,
"is_parallel": true,
"self": 0.0006948689999717317,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037876500005040725,
"count": 1,
"is_parallel": true,
"self": 0.00037876500005040725
},
"communicator.exchange": {
"total": 0.03213461499990444,
"count": 1,
"is_parallel": true,
"self": 0.03213461499990444
},
"steps_from_proto": {
"total": 0.0018632989999787242,
"count": 1,
"is_parallel": true,
"self": 0.00037148600040382007,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001491812999574904,
"count": 10,
"is_parallel": true,
"self": 0.001491812999574904
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 209.98767695698007,
"count": 18198,
"is_parallel": true,
"self": 9.86589984297143,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.039812680003934,
"count": 18198,
"is_parallel": true,
"self": 5.039812680003934
},
"communicator.exchange": {
"total": 163.18081332399765,
"count": 18198,
"is_parallel": true,
"self": 163.18081332399765
},
"steps_from_proto": {
"total": 31.90115111000705,
"count": 18198,
"is_parallel": true,
"self": 5.842529619007564,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.058621490999485,
"count": 181980,
"is_parallel": true,
"self": 26.058621490999485
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.8993000064001535e-05,
"count": 1,
"self": 4.8993000064001535e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 416.77163372898144,
"count": 659572,
"is_parallel": true,
"self": 14.51988568290949,
"children": {
"process_trajectory": {
"total": 230.80327966307027,
"count": 659572,
"is_parallel": true,
"self": 230.31921503607032,
"children": {
"RLTrainer._checkpoint": {
"total": 0.48406462699995245,
"count": 4,
"is_parallel": true,
"self": 0.48406462699995245
}
}
},
"_update_policy": {
"total": 171.44846838300168,
"count": 90,
"is_parallel": true,
"self": 49.14965775400583,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.29881062899585,
"count": 4587,
"is_parallel": true,
"self": 122.29881062899585
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09606466599984742,
"count": 1,
"self": 0.0009081829998649482,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09515648299998247,
"count": 1,
"self": 0.09515648299998247
}
}
}
}
}
}
}