ppo-Pyramids / run_logs /timers.json
ARandomFrenchDev's picture
add: added model v1
2b48be8
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.2916024625301361,
"min": 0.29125112295150757,
"max": 1.415248155593872,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 8827.3896484375,
"min": 8746.53125,
"max": 42932.96875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989916.0,
"min": 29956.0,
"max": 989916.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989916.0,
"min": 29956.0,
"max": 989916.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5374546647071838,
"min": -0.112742580473423,
"max": 0.5798947811126709,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 149.94985961914062,
"min": -27.396446228027344,
"max": 164.1102294921875,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.027990568429231644,
"min": -0.018696676939725876,
"max": 0.546489417552948,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 7.80936861038208,
"min": -5.291159629821777,
"max": 130.06448364257812,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06590100508365854,
"min": 0.06518899585654847,
"max": 0.07228057705645621,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9226140711712195,
"min": 0.48423678529764597,
"max": 1.0717440580437871,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014334958537485964,
"min": 0.0006781006875537126,
"max": 0.01931471981436192,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2006894195248035,
"min": 0.009493409625751976,
"max": 0.2271763084084823,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.552490339678574e-06,
"min": 7.552490339678574e-06,
"max": 0.0002952382301586857,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010573486475550004,
"min": 0.00010573486475550004,
"max": 0.003374662075112699,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10251746428571429,
"min": 0.10251746428571429,
"max": 0.19841274285714286,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4352445,
"min": 1.3888892,
"max": 2.4441998,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026149468214285726,
"min": 0.00026149468214285726,
"max": 0.009841433011428572,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003660925550000002,
"min": 0.003660925550000002,
"max": 0.11250624127,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.014703771099448204,
"min": 0.014703771099448204,
"max": 0.6592143177986145,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.20585279166698456,
"min": 0.20585279166698456,
"max": 4.614500045776367,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 359.95180722891564,
"min": 323.93548387096774,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29876.0,
"min": 16627.0,
"max": 33226.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.543631308409105,
"min": -0.9999750521965325,
"max": 1.654556972525453,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 128.1213985979557,
"min": -31.99920167028904,
"max": 153.87379844486713,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.543631308409105,
"min": -0.9999750521965325,
"max": 1.654556972525453,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 128.1213985979557,
"min": -31.99920167028904,
"max": 153.87379844486713,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.052627474275426044,
"min": 0.05192310863765337,
"max": 13.408304013311863,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.368080364860361,
"min": 4.368080364860361,
"max": 227.94116822630167,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1675370621",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1675372936"
},
"total": 2314.935416526,
"count": 1,
"self": 0.424498188000598,
"children": {
"run_training.setup": {
"total": 0.0995371310000337,
"count": 1,
"self": 0.0995371310000337
},
"TrainerController.start_learning": {
"total": 2314.4113812069995,
"count": 1,
"self": 1.4329393200418963,
"children": {
"TrainerController._reset_env": {
"total": 6.065273781000087,
"count": 1,
"self": 6.065273781000087
},
"TrainerController.advance": {
"total": 2306.8241047359575,
"count": 63875,
"self": 1.5366646640513864,
"children": {
"env_step": {
"total": 1563.27048306198,
"count": 63875,
"self": 1443.6524094129186,
"children": {
"SubprocessEnvManager._take_step": {
"total": 118.70890929300504,
"count": 63875,
"self": 4.7884965320454285,
"children": {
"TorchPolicy.evaluate": {
"total": 113.92041276095961,
"count": 62563,
"self": 37.60675069903573,
"children": {
"TorchPolicy.sample_actions": {
"total": 76.31366206192388,
"count": 62563,
"self": 76.31366206192388
}
}
}
}
},
"workers": {
"total": 0.909164356056408,
"count": 63875,
"self": 0.0,
"children": {
"worker_root": {
"total": 2309.067326014983,
"count": 63875,
"is_parallel": true,
"self": 983.1047408640052,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017364709997309546,
"count": 1,
"is_parallel": true,
"self": 0.0006073059989830654,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011291650007478893,
"count": 8,
"is_parallel": true,
"self": 0.0011291650007478893
}
}
},
"UnityEnvironment.step": {
"total": 0.04667686200036769,
"count": 1,
"is_parallel": true,
"self": 0.0005168470001990499,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046899800008759485,
"count": 1,
"is_parallel": true,
"self": 0.00046899800008759485
},
"communicator.exchange": {
"total": 0.044000779000270995,
"count": 1,
"is_parallel": true,
"self": 0.044000779000270995
},
"steps_from_proto": {
"total": 0.0016902379998100514,
"count": 1,
"is_parallel": true,
"self": 0.0004548000001705077,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012354379996395437,
"count": 8,
"is_parallel": true,
"self": 0.0012354379996395437
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1325.9625851509777,
"count": 63874,
"is_parallel": true,
"self": 27.962366246931197,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.755823151074765,
"count": 63874,
"is_parallel": true,
"self": 23.755823151074765
},
"communicator.exchange": {
"total": 1168.9903366930162,
"count": 63874,
"is_parallel": true,
"self": 1168.9903366930162
},
"steps_from_proto": {
"total": 105.25405905995558,
"count": 63874,
"is_parallel": true,
"self": 23.855910272091478,
"children": {
"_process_rank_one_or_two_observation": {
"total": 81.3981487878641,
"count": 510992,
"is_parallel": true,
"self": 81.3981487878641
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 742.016957009926,
"count": 63875,
"self": 2.7526073689764416,
"children": {
"process_trajectory": {
"total": 170.82747540094806,
"count": 63875,
"self": 170.63323539894736,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19424000200069713,
"count": 2,
"self": 0.19424000200069713
}
}
},
"_update_policy": {
"total": 568.4368742400015,
"count": 449,
"self": 220.59458261598866,
"children": {
"TorchPPOOptimizer.update": {
"total": 347.8422916240129,
"count": 22839,
"self": 347.8422916240129
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1180000001331791e-06,
"count": 1,
"self": 1.1180000001331791e-06
},
"TrainerController._save_models": {
"total": 0.08906225200007611,
"count": 1,
"self": 0.0014762419996259268,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08758601000045019,
"count": 1,
"self": 0.08758601000045019
}
}
}
}
}
}
}