uyenvuong's picture
First Push
483f043
raw
history blame
18.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9053978323936462,
"min": 0.9053978323936462,
"max": 2.857614278793335,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8634.779296875,
"min": 8634.779296875,
"max": 29484.86328125,
"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": 12.707003593444824,
"min": 0.37076127529144287,
"max": 12.719487190246582,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2477.86572265625,
"min": 71.92768859863281,
"max": 2594.775390625,
"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": 0.071774666421726,
"min": 0.06401261230360022,
"max": 0.07485213053901224,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.287098665686904,
"min": 0.25745292735033826,
"max": 0.3742606526950612,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2040013282322416,
"min": 0.1420534659524028,
"max": 0.29638315620375616,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8160053129289664,
"min": 0.5682138638096113,
"max": 1.4022927856912801,
"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": 24.886363636363637,
"min": 3.9545454545454546,
"max": 24.886363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1095.0,
"min": 174.0,
"max": 1354.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.886363636363637,
"min": 3.9545454545454546,
"max": 24.886363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1095.0,
"min": 174.0,
"max": 1354.0,
"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": "1680146553",
"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": "1680147011"
},
"total": 457.23983078699996,
"count": 1,
"self": 0.3810780879999811,
"children": {
"run_training.setup": {
"total": 0.11070823000000019,
"count": 1,
"self": 0.11070823000000019
},
"TrainerController.start_learning": {
"total": 456.748044469,
"count": 1,
"self": 0.48623722399611324,
"children": {
"TrainerController._reset_env": {
"total": 9.214981886000032,
"count": 1,
"self": 9.214981886000032
},
"TrainerController.advance": {
"total": 446.90351820300384,
"count": 18200,
"self": 0.2618266029851384,
"children": {
"env_step": {
"total": 446.6416916000187,
"count": 18200,
"self": 322.81298740299735,
"children": {
"SubprocessEnvManager._take_step": {
"total": 123.5754922900145,
"count": 18200,
"self": 2.045820865030919,
"children": {
"TorchPolicy.evaluate": {
"total": 121.52967142498358,
"count": 18200,
"self": 121.52967142498358
}
}
},
"workers": {
"total": 0.2532119070068575,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 455.3075349059882,
"count": 18200,
"is_parallel": true,
"self": 218.9494394099861,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0049103119999927,
"count": 1,
"is_parallel": true,
"self": 0.0033936530003302323,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001516658999662468,
"count": 10,
"is_parallel": true,
"self": 0.001516658999662468
}
}
},
"UnityEnvironment.step": {
"total": 0.03301284700000906,
"count": 1,
"is_parallel": true,
"self": 0.000547617000165701,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002989309999748002,
"count": 1,
"is_parallel": true,
"self": 0.0002989309999748002
},
"communicator.exchange": {
"total": 0.03034990999992715,
"count": 1,
"is_parallel": true,
"self": 0.03034990999992715
},
"steps_from_proto": {
"total": 0.0018163889999414096,
"count": 1,
"is_parallel": true,
"self": 0.00036076999992928904,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014556190000121205,
"count": 10,
"is_parallel": true,
"self": 0.0014556190000121205
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 236.35809549600208,
"count": 18199,
"is_parallel": true,
"self": 9.441296685010911,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.134989412994855,
"count": 18199,
"is_parallel": true,
"self": 5.134989412994855
},
"communicator.exchange": {
"total": 190.8962884429959,
"count": 18199,
"is_parallel": true,
"self": 190.8962884429959
},
"steps_from_proto": {
"total": 30.885520955000402,
"count": 18199,
"is_parallel": true,
"self": 6.050780276995511,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.83474067800489,
"count": 181990,
"is_parallel": true,
"self": 24.83474067800489
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00010420800003885233,
"count": 1,
"self": 0.00010420800003885233,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 443.52300827092085,
"count": 398321,
"is_parallel": true,
"self": 9.873967624953025,
"children": {
"process_trajectory": {
"total": 246.6853485299689,
"count": 398321,
"is_parallel": true,
"self": 245.118863901969,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5664846279998983,
"count": 4,
"is_parallel": true,
"self": 1.5664846279998983
}
}
},
"_update_policy": {
"total": 186.96369211599892,
"count": 90,
"is_parallel": true,
"self": 70.29396110999937,
"children": {
"TorchPPOOptimizer.update": {
"total": 116.66973100599955,
"count": 4587,
"is_parallel": true,
"self": 116.66973100599955
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1432029479999528,
"count": 1,
"self": 0.0011684909998166404,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14203445700013617,
"count": 1,
"self": 0.14203445700013617
}
}
}
}
}
}
}