Felipe474's picture
First training of SnowballTarget
dfdb2a1
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.862683892250061,
"min": 0.862683892250061,
"max": 2.859825849533081,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8284.353515625,
"min": 8284.353515625,
"max": 29318.93359375,
"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": 12.976241111755371,
"min": 0.28392869234085083,
"max": 13.004122734069824,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2530.366943359375,
"min": 55.0821647644043,
"max": 2644.36376953125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07272248257090813,
"min": 0.06200557554725046,
"max": 0.07514601610798541,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2908899302836325,
"min": 0.2594349912894769,
"max": 0.375730080539927,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19157332711506123,
"min": 0.13153012817743798,
"max": 0.2983127167704059,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7662933084602449,
"min": 0.5261205127097519,
"max": 1.477063180130048,
"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": 25.772727272727273,
"min": 3.6136363636363638,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1134.0,
"min": 159.0,
"max": 1413.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.772727272727273,
"min": 3.6136363636363638,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1134.0,
"min": 159.0,
"max": 1413.0,
"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": "1679405988",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1679406484"
},
"total": 495.58106602199996,
"count": 1,
"self": 0.754545389999862,
"children": {
"run_training.setup": {
"total": 0.12419515500005218,
"count": 1,
"self": 0.12419515500005218
},
"TrainerController.start_learning": {
"total": 494.70232547700004,
"count": 1,
"self": 0.6038276220216403,
"children": {
"TrainerController._reset_env": {
"total": 9.681649167000046,
"count": 1,
"self": 9.681649167000046
},
"TrainerController.advance": {
"total": 484.1936772219784,
"count": 18223,
"self": 0.3134840329856843,
"children": {
"env_step": {
"total": 483.88019318899273,
"count": 18223,
"self": 346.66690437199236,
"children": {
"SubprocessEnvManager._take_step": {
"total": 136.90837012400152,
"count": 18223,
"self": 2.0763804319891506,
"children": {
"TorchPolicy.evaluate": {
"total": 134.83198969201237,
"count": 18223,
"self": 134.83198969201237
}
}
},
"workers": {
"total": 0.30491869299885366,
"count": 18223,
"self": 0.0,
"children": {
"worker_root": {
"total": 493.07863199100336,
"count": 18223,
"is_parallel": true,
"self": 237.27309759999412,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005025471999942965,
"count": 1,
"is_parallel": true,
"self": 0.0033987229996910173,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001626749000251948,
"count": 10,
"is_parallel": true,
"self": 0.001626749000251948
}
}
},
"UnityEnvironment.step": {
"total": 0.03708797199999481,
"count": 1,
"is_parallel": true,
"self": 0.0004129469999725188,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004145899999912217,
"count": 1,
"is_parallel": true,
"self": 0.0004145899999912217
},
"communicator.exchange": {
"total": 0.03430821500001002,
"count": 1,
"is_parallel": true,
"self": 0.03430821500001002
},
"steps_from_proto": {
"total": 0.0019522200000210432,
"count": 1,
"is_parallel": true,
"self": 0.0003883110000515444,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015639089999694988,
"count": 10,
"is_parallel": true,
"self": 0.0015639089999694988
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 255.80553439100925,
"count": 18222,
"is_parallel": true,
"self": 9.830668138019178,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.587074445991107,
"count": 18222,
"is_parallel": true,
"self": 5.587074445991107
},
"communicator.exchange": {
"total": 206.3895982680067,
"count": 18222,
"is_parallel": true,
"self": 206.3895982680067
},
"steps_from_proto": {
"total": 33.99819353899227,
"count": 18222,
"is_parallel": true,
"self": 6.881307840032264,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.116885698960004,
"count": 182220,
"is_parallel": true,
"self": 27.116885698960004
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016528299988749495,
"count": 1,
"self": 0.00016528299988749495,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 480.31478112799937,
"count": 430613,
"is_parallel": true,
"self": 11.30173059892411,
"children": {
"process_trajectory": {
"total": 267.8293263320761,
"count": 430613,
"is_parallel": true,
"self": 265.4265060420763,
"children": {
"RLTrainer._checkpoint": {
"total": 2.402820289999795,
"count": 4,
"is_parallel": true,
"self": 2.402820289999795
}
}
},
"_update_policy": {
"total": 201.18372419699915,
"count": 90,
"is_parallel": true,
"self": 71.22683542199456,
"children": {
"TorchPPOOptimizer.update": {
"total": 129.9568887750046,
"count": 4584,
"is_parallel": true,
"self": 129.9568887750046
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.22300618300005226,
"count": 1,
"self": 0.0013268130001051759,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22167936999994708,
"count": 1,
"self": 0.22167936999994708
}
}
}
}
}
}
}