ppo-PyramidsRND / run_logs /timers.json
yoyoh's picture
First Push
a1b66b3 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.14496247470378876,
"min": 0.14172488451004028,
"max": 1.4602644443511963,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 4348.8740234375,
"min": 4267.61962890625,
"max": 44298.58203125,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999983.0,
"min": 29952.0,
"max": 2999983.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999983.0,
"min": 29952.0,
"max": 2999983.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.9060383439064026,
"min": -0.08761407434940338,
"max": 0.9356099367141724,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 282.6839599609375,
"min": -21.114992141723633,
"max": 294.7171325683594,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.025039682164788246,
"min": -0.031877681612968445,
"max": 0.1727130115032196,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 7.812380790710449,
"min": -9.56330394744873,
"max": 41.623836517333984,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07232827505031413,
"min": 0.06347589382979398,
"max": 0.07591784955365147,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0125958507043977,
"min": 0.502719995540623,
"max": 1.0628498937511206,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013410299918819769,
"min": 0.0007182466045029113,
"max": 0.01715485240995241,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.18774419886347676,
"min": 0.006464219440526202,
"max": 0.24016793373933373,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.4934637879261848e-06,
"min": 1.4934637879261848e-06,
"max": 0.00029838354339596195,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.090849303096659e-05,
"min": 2.090849303096659e-05,
"max": 0.0041175434274855665,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10049778809523811,
"min": 0.10049778809523811,
"max": 0.19946118095238097,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4069690333333336,
"min": 1.3962282666666668,
"max": 2.8725144333333335,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 5.972903071428551e-05,
"min": 5.972903071428551e-05,
"max": 0.009946171977142856,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008362064299999971,
"min": 0.0008362064299999971,
"max": 0.13726419189,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.007255134638398886,
"min": 0.007148280274122953,
"max": 0.34253978729248047,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.10157188773155212,
"min": 0.10007592290639877,
"max": 2.3977785110473633,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 199.74,
"min": 190.73202614379085,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29961.0,
"min": 15984.0,
"max": 32448.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7865536318512152,
"min": -1.0000000521540642,
"max": 1.8078509149899393,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 269.7695984095335,
"min": -31.999601677060127,
"max": 291.06399731338024,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7865536318512152,
"min": -1.0000000521540642,
"max": 1.8078509149899393,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 269.7695984095335,
"min": -31.999601677060127,
"max": 291.06399731338024,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.014884475416175031,
"min": 0.014144451745142445,
"max": 6.292244049720466,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.2475557878424297,
"min": 2.164101117006794,
"max": 100.67590479552746,
"count": 100
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1742996867",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/samrito/anaconda3/envs/drl_hf/bin/mlagents-learn ./PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1742999094"
},
"total": 2227.129396221135,
"count": 1,
"self": 0.16708244499750435,
"children": {
"run_training.setup": {
"total": 0.008784729987382889,
"count": 1,
"self": 0.008784729987382889
},
"TrainerController.start_learning": {
"total": 2226.95352904615,
"count": 1,
"self": 2.097828549798578,
"children": {
"TrainerController._reset_env": {
"total": 1.031348034972325,
"count": 1,
"self": 1.031348034972325
},
"TrainerController.advance": {
"total": 2223.788404432591,
"count": 196331,
"self": 1.9410254671238363,
"children": {
"env_step": {
"total": 1499.2461569115985,
"count": 196331,
"self": 1314.240069488762,
"children": {
"SubprocessEnvManager._take_step": {
"total": 183.77612575888634,
"count": 196331,
"self": 6.455824406351894,
"children": {
"TorchPolicy.evaluate": {
"total": 177.32030135253444,
"count": 187560,
"self": 177.32030135253444
}
}
},
"workers": {
"total": 1.2299616639502347,
"count": 196331,
"self": 0.0,
"children": {
"worker_root": {
"total": 2224.288494676817,
"count": 196331,
"is_parallel": true,
"self": 1045.1043580591213,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012069069780409336,
"count": 1,
"is_parallel": true,
"self": 0.00034651486203074455,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008603921160101891,
"count": 8,
"is_parallel": true,
"self": 0.0008603921160101891
}
}
},
"UnityEnvironment.step": {
"total": 0.014888166915625334,
"count": 1,
"is_parallel": true,
"self": 0.00015027285553514957,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00013927603140473366,
"count": 1,
"is_parallel": true,
"self": 0.00013927603140473366
},
"communicator.exchange": {
"total": 0.014178520999848843,
"count": 1,
"is_parallel": true,
"self": 0.014178520999848843
},
"steps_from_proto": {
"total": 0.00042009702883660793,
"count": 1,
"is_parallel": true,
"self": 0.00010130810551345348,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00031878892332315445,
"count": 8,
"is_parallel": true,
"self": 0.00031878892332315445
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1179.184136617696,
"count": 196330,
"is_parallel": true,
"self": 27.99044243968092,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 17.395500971237198,
"count": 196330,
"is_parallel": true,
"self": 17.395500971237198
},
"communicator.exchange": {
"total": 1057.8101731513161,
"count": 196330,
"is_parallel": true,
"self": 1057.8101731513161
},
"steps_from_proto": {
"total": 75.98802005546167,
"count": 196330,
"is_parallel": true,
"self": 17.393637699307874,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.5943823561538,
"count": 1570640,
"is_parallel": true,
"self": 58.5943823561538
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 722.6012220538687,
"count": 196331,
"self": 3.9939864960033447,
"children": {
"process_trajectory": {
"total": 154.7143792838324,
"count": 196331,
"self": 154.4588273372501,
"children": {
"RLTrainer._checkpoint": {
"total": 0.25555194658227265,
"count": 6,
"self": 0.25555194658227265
}
}
},
"_update_policy": {
"total": 563.892856274033,
"count": 1398,
"self": 317.67795963049866,
"children": {
"TorchPPOOptimizer.update": {
"total": 246.2148966435343,
"count": 68409,
"self": 246.2148966435343
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.828907549381256e-07,
"count": 1,
"self": 4.828907549381256e-07
},
"TrainerController._save_models": {
"total": 0.035947545897215605,
"count": 1,
"self": 0.0006111199036240578,
"children": {
"RLTrainer._checkpoint": {
"total": 0.03533642599359155,
"count": 1,
"self": 0.03533642599359155
}
}
}
}
}
}
}