dylwil3's picture
First Push
915a32d
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8796435594558716,
"min": 0.8796435594558716,
"max": 2.874730348587036,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8398.8369140625,
"min": 8398.8369140625,
"max": 29503.357421875,
"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": 11.949553489685059,
"min": 0.4006459414958954,
"max": 11.949553489685059,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2330.162841796875,
"min": 77.72531127929688,
"max": 2390.300048828125,
"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": 0.07093508278551014,
"min": 0.06318095230837535,
"max": 0.07434265029347248,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28374033114204056,
"min": 0.2586352496086072,
"max": 0.3669808570312122,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19263924293073953,
"min": 0.0977764114162282,
"max": 0.28371842334083486,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7705569717229581,
"min": 0.3911056456649128,
"max": 1.4185921167041742,
"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": 23.75,
"min": 2.9318181818181817,
"max": 23.75,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1045.0,
"min": 129.0,
"max": 1298.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.75,
"min": 2.9318181818181817,
"max": 23.75,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1045.0,
"min": 129.0,
"max": 1298.0,
"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": "1681750348",
"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": "1681750840"
},
"total": 492.26550580699995,
"count": 1,
"self": 0.38270820799994,
"children": {
"run_training.setup": {
"total": 0.11930264300008275,
"count": 1,
"self": 0.11930264300008275
},
"TrainerController.start_learning": {
"total": 491.76349495599993,
"count": 1,
"self": 0.5943944970052826,
"children": {
"TrainerController._reset_env": {
"total": 4.14384816300003,
"count": 1,
"self": 4.14384816300003
},
"TrainerController.advance": {
"total": 486.8841457499947,
"count": 18201,
"self": 0.3177454289881325,
"children": {
"env_step": {
"total": 486.56640032100654,
"count": 18201,
"self": 356.00792787599255,
"children": {
"SubprocessEnvManager._take_step": {
"total": 130.2537198669911,
"count": 18201,
"self": 1.7890449479787094,
"children": {
"TorchPolicy.evaluate": {
"total": 128.4646749190124,
"count": 18201,
"self": 128.4646749190124
}
}
},
"workers": {
"total": 0.30475257802288525,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 490.118747296999,
"count": 18201,
"is_parallel": true,
"self": 224.770119810006,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004802494000045954,
"count": 1,
"is_parallel": true,
"self": 0.0031712030000790037,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00163129099996695,
"count": 10,
"is_parallel": true,
"self": 0.00163129099996695
}
}
},
"UnityEnvironment.step": {
"total": 0.11209394299999076,
"count": 1,
"is_parallel": true,
"self": 0.0006921109999211694,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004330840000648095,
"count": 1,
"is_parallel": true,
"self": 0.0004330840000648095
},
"communicator.exchange": {
"total": 0.1088997819999804,
"count": 1,
"is_parallel": true,
"self": 0.1088997819999804
},
"steps_from_proto": {
"total": 0.002068966000024375,
"count": 1,
"is_parallel": true,
"self": 0.0005746600002112245,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014943059998131503,
"count": 10,
"is_parallel": true,
"self": 0.0014943059998131503
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 265.348627486993,
"count": 18200,
"is_parallel": true,
"self": 10.621866455993768,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.974219219998304,
"count": 18200,
"is_parallel": true,
"self": 5.974219219998304
},
"communicator.exchange": {
"total": 213.37218295400396,
"count": 18200,
"is_parallel": true,
"self": 213.37218295400396
},
"steps_from_proto": {
"total": 35.38035885699696,
"count": 18200,
"is_parallel": true,
"self": 7.256104677987764,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.1242541790092,
"count": 182000,
"is_parallel": true,
"self": 28.1242541790092
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015404300006593985,
"count": 1,
"self": 0.00015404300006593985,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 483.0121012049872,
"count": 445485,
"is_parallel": true,
"self": 11.252907552102783,
"children": {
"process_trajectory": {
"total": 269.25976081988506,
"count": 445485,
"is_parallel": true,
"self": 267.6009561978849,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6588046220001615,
"count": 4,
"is_parallel": true,
"self": 1.6588046220001615
}
}
},
"_update_policy": {
"total": 202.49943283299933,
"count": 90,
"is_parallel": true,
"self": 73.66550509599904,
"children": {
"TorchPPOOptimizer.update": {
"total": 128.8339277370003,
"count": 4587,
"is_parallel": true,
"self": 128.8339277370003
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14095250299988038,
"count": 1,
"self": 0.0010156189998724585,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13993688400000792,
"count": 1,
"self": 0.13993688400000792
}
}
}
}
}
}
}