abragin's picture
First Push
f06b3e9 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9875412583351135,
"min": 0.9875412583351135,
"max": 2.8665339946746826,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9429.0439453125,
"min": 9429.0439453125,
"max": 29356.173828125,
"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": 12.99604320526123,
"min": 0.3783890902996063,
"max": 12.99604320526123,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2534.228515625,
"min": 73.40748596191406,
"max": 2636.926513671875,
"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": 0.06822154511624545,
"min": 0.06070370793103769,
"max": 0.07323385967631074,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2728861804649818,
"min": 0.24281483172415075,
"max": 0.36359573484115376,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1968732571192816,
"min": 0.12415897930794231,
"max": 0.2795068551512325,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7874930284771264,
"min": 0.49663591723176925,
"max": 1.3884807784183353,
"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": 25.863636363636363,
"min": 3.25,
"max": 25.863636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1138.0,
"min": 143.0,
"max": 1407.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.863636363636363,
"min": 3.25,
"max": 25.863636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1138.0,
"min": 143.0,
"max": 1407.0,
"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": "1706873671",
"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": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1706874170"
},
"total": 498.43838579699997,
"count": 1,
"self": 0.7470850009999594,
"children": {
"run_training.setup": {
"total": 0.08286648300003208,
"count": 1,
"self": 0.08286648300003208
},
"TrainerController.start_learning": {
"total": 497.608434313,
"count": 1,
"self": 0.7055010100033314,
"children": {
"TrainerController._reset_env": {
"total": 3.4292857050000407,
"count": 1,
"self": 3.4292857050000407
},
"TrainerController.advance": {
"total": 493.3355872789967,
"count": 18206,
"self": 0.34908764299564154,
"children": {
"env_step": {
"total": 492.98649963600104,
"count": 18206,
"self": 319.7270391110055,
"children": {
"SubprocessEnvManager._take_step": {
"total": 172.90794593600106,
"count": 18206,
"self": 1.6765738400100645,
"children": {
"TorchPolicy.evaluate": {
"total": 171.231372095991,
"count": 18206,
"self": 171.231372095991
}
}
},
"workers": {
"total": 0.351514588994462,
"count": 18206,
"self": 0.0,
"children": {
"worker_root": {
"total": 496.05193022300625,
"count": 18206,
"is_parallel": true,
"self": 243.85484759599393,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0050575079999930495,
"count": 1,
"is_parallel": true,
"self": 0.003400319999968815,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016571880000242345,
"count": 10,
"is_parallel": true,
"self": 0.0016571880000242345
}
}
},
"UnityEnvironment.step": {
"total": 0.057161580000013146,
"count": 1,
"is_parallel": true,
"self": 0.000765800999943167,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005159640000442778,
"count": 1,
"is_parallel": true,
"self": 0.0005159640000442778
},
"communicator.exchange": {
"total": 0.05316324099999292,
"count": 1,
"is_parallel": true,
"self": 0.05316324099999292
},
"steps_from_proto": {
"total": 0.0027165740000327787,
"count": 1,
"is_parallel": true,
"self": 0.0007083149999971283,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020082590000356504,
"count": 10,
"is_parallel": true,
"self": 0.0020082590000356504
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 252.19708262701232,
"count": 18205,
"is_parallel": true,
"self": 11.812334025030168,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.2148851790066715,
"count": 18205,
"is_parallel": true,
"self": 6.2148851790066715
},
"communicator.exchange": {
"total": 195.4385673559944,
"count": 18205,
"is_parallel": true,
"self": 195.4385673559944
},
"steps_from_proto": {
"total": 38.73129606698109,
"count": 18205,
"is_parallel": true,
"self": 7.555294192981307,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.17600187399978,
"count": 182050,
"is_parallel": true,
"self": 31.17600187399978
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015482699996027804,
"count": 1,
"self": 0.00015482699996027804,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 486.8693623179302,
"count": 741502,
"is_parallel": true,
"self": 17.07980968692135,
"children": {
"process_trajectory": {
"total": 269.4863573910098,
"count": 741502,
"is_parallel": true,
"self": 268.32404442200965,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1623129690001406,
"count": 4,
"is_parallel": true,
"self": 1.1623129690001406
}
}
},
"_update_policy": {
"total": 200.30319523999907,
"count": 90,
"is_parallel": true,
"self": 56.122082165003576,
"children": {
"TorchPPOOptimizer.update": {
"total": 144.1811130749955,
"count": 4587,
"is_parallel": true,
"self": 144.1811130749955
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13790549199995894,
"count": 1,
"self": 0.0013418249999403997,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13656366700001854,
"count": 1,
"self": 0.13656366700001854
}
}
}
}
}
}
}