patonw's picture
Baseline
48051ae
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.1804736852645874,
"min": 1.1804736852645874,
"max": 2.8626716136932373,
"count": 10
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 58900.91796875,
"min": 58900.91796875,
"max": 144599.265625,
"count": 10
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 49936.0,
"max": 499976.0,
"count": 10
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 49936.0,
"max": 499976.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 11.168292045593262,
"min": 0.26721879839897156,
"max": 11.168292045593262,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 11201.796875,
"min": 265.0810546875,
"max": 11201.796875,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 50347.0,
"min": 48158.0,
"max": 50347.0,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 23.25296442687747,
"min": 3.7892561983471076,
"max": 23.25296442687747,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 5883.0,
"min": 917.0,
"max": 5883.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.25296442687747,
"min": 3.7892561983471076,
"max": 23.25296442687747,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 5883.0,
"min": 917.0,
"max": 5883.0,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.02497695688798558,
"min": 0.02214559779730886,
"max": 0.025577116236672737,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.09990782755194232,
"min": 0.09014036386039759,
"max": 0.12788558118336368,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.259774170940121,
"min": 0.12491041819254556,
"max": 0.3170946991443634,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.039096683760484,
"min": 0.49964167277018223,
"max": 1.585473495721817,
"count": 10
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.4576495141199999e-05,
"min": 1.4576495141199999e-05,
"max": 0.0002841864052712,
"count": 10
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.8305980564799996e-05,
"min": 5.8305980564799996e-05,
"max": 0.0012797184734271998,
"count": 10
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1048588,
"min": 0.1048588,
"max": 0.19472879999999998,
"count": 10
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4194352,
"min": 0.4194352,
"max": 0.9265728000000001,
"count": 10
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00025245412000000005,
"min": 0.00025245412000000005,
"max": 0.004736967120000001,
"count": 10
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0010098164800000002,
"min": 0.0010098164800000002,
"max": 0.02133598272,
"count": 10
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1691535835",
"python_version": "3.9.0 | packaged by conda-forge | (default, Nov 26 2020, 07:57:39) \n[GCC 9.3.0]",
"command_line_arguments": "/home/patonw/code/Unity/ml-agents/.mamba/envs/my-mamba-environment/bin/mlagents-learn --env envs/SnowballTarget/SnowballTarget --run-id SnowballTarget-00 --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+cu113",
"numpy_version": "1.21.2",
"end_time_seconds": "1691536233"
},
"total": 397.5904882770001,
"count": 1,
"self": 0.16756914499910636,
"children": {
"run_training.setup": {
"total": 0.009706085000289022,
"count": 1,
"self": 0.009706085000289022
},
"TrainerController.start_learning": {
"total": 397.4132130470007,
"count": 1,
"self": 0.4216114859382287,
"children": {
"TrainerController._reset_env": {
"total": 2.8039782200003174,
"count": 1,
"self": 2.8039782200003174
},
"TrainerController.advance": {
"total": 394.12958664506186,
"count": 45464,
"self": 0.4558704629644126,
"children": {
"env_step": {
"total": 299.8565515001337,
"count": 45464,
"self": 234.38348336796116,
"children": {
"SubprocessEnvManager._take_step": {
"total": 65.17549070208679,
"count": 45464,
"self": 2.199336155135825,
"children": {
"TorchPolicy.evaluate": {
"total": 62.976154546950966,
"count": 45464,
"self": 62.976154546950966
}
}
},
"workers": {
"total": 0.29757743008576654,
"count": 45464,
"self": 0.0,
"children": {
"worker_root": {
"total": 396.46577788996547,
"count": 45464,
"is_parallel": true,
"self": 189.33736107609184,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008597330006523407,
"count": 1,
"is_parallel": true,
"self": 0.00023353200140263652,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006262009992497042,
"count": 10,
"is_parallel": true,
"self": 0.0006262009992497042
}
}
},
"UnityEnvironment.step": {
"total": 0.01475060999928246,
"count": 1,
"is_parallel": true,
"self": 0.00021816299886268098,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001838770003814716,
"count": 1,
"is_parallel": true,
"self": 0.0001838770003814716
},
"communicator.exchange": {
"total": 0.013640483000017412,
"count": 1,
"is_parallel": true,
"self": 0.013640483000017412
},
"steps_from_proto": {
"total": 0.0007080870000208961,
"count": 1,
"is_parallel": true,
"self": 0.0001470200013500289,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005610669986708672,
"count": 10,
"is_parallel": true,
"self": 0.0005610669986708672
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 207.12841681387363,
"count": 45463,
"is_parallel": true,
"self": 8.808891418884741,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.620152991976283,
"count": 45463,
"is_parallel": true,
"self": 4.620152991976283
},
"communicator.exchange": {
"total": 166.25211986397517,
"count": 45463,
"is_parallel": true,
"self": 166.25211986397517
},
"steps_from_proto": {
"total": 27.447252539037436,
"count": 45463,
"is_parallel": true,
"self": 5.631530266500704,
"children": {
"_process_rank_one_or_two_observation": {
"total": 21.815722272536732,
"count": 454630,
"is_parallel": true,
"self": 21.815722272536732
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 93.81716468196373,
"count": 45464,
"self": 0.5347448609354615,
"children": {
"process_trajectory": {
"total": 26.373823229029767,
"count": 45464,
"self": 26.30473765602983,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06908557299993845,
"count": 1,
"self": 0.06908557299993845
}
}
},
"_update_policy": {
"total": 66.9085965919985,
"count": 47,
"self": 55.835941368975,
"children": {
"TorchPPOOptimizer.update": {
"total": 11.072655223023503,
"count": 1410,
"self": 11.072655223023503
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.510000846697949e-07,
"count": 1,
"self": 5.510000846697949e-07
},
"TrainerController._save_models": {
"total": 0.05803614500018739,
"count": 1,
"self": 0.00026971900024364004,
"children": {
"RLTrainer._checkpoint": {
"total": 0.05776642599994375,
"count": 1,
"self": 0.05776642599994375
}
}
}
}
}
}
}