ppo-PyramidsRND / run_logs /timers.json
matthh's picture
First Push
5edb763
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3414716124534607,
"min": 0.32259008288383484,
"max": 1.4840004444122314,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 10358.8828125,
"min": 9538.34375,
"max": 45018.63671875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989974.0,
"min": 29952.0,
"max": 989974.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989974.0,
"min": 29952.0,
"max": 989974.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.682823121547699,
"min": -0.09507901966571808,
"max": 0.682823121547699,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 200.06716918945312,
"min": -22.914043426513672,
"max": 200.06716918945312,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.019967222586274147,
"min": 0.0079377181828022,
"max": 0.31547167897224426,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 5.850396156311035,
"min": 2.206685781478882,
"max": 76.02867126464844,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0693158276622211,
"min": 0.06421594525692965,
"max": 0.07293356853341922,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9704215872710954,
"min": 0.4892266017658135,
"max": 1.0666300030921667,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.018169651857426607,
"min": 0.00021790476021594195,
"max": 0.018169651857426607,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2543751260039725,
"min": 0.0028327618828072453,
"max": 0.2543751260039725,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.370626114585719e-06,
"min": 7.370626114585719e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010318876560420006,
"min": 0.00010318876560420006,
"max": 0.0037583272472242993,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10245684285714286,
"min": 0.10245684285714286,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4343958,
"min": 1.3886848,
"max": 2.6527757,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002554386014285716,
"min": 0.0002554386014285716,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0035761404200000024,
"min": 0.0035761404200000024,
"max": 0.12529229243,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.013896447606384754,
"min": 0.013896447606384754,
"max": 0.591275691986084,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1945502609014511,
"min": 0.1945502609014511,
"max": 4.138929843902588,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 273.3162393162393,
"min": 273.3162393162393,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31978.0,
"min": 15984.0,
"max": 33768.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6924820330917325,
"min": -1.0000000521540642,
"max": 1.6956217682892734,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 198.0203978717327,
"min": -31.99320164322853,
"max": 198.0203978717327,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6924820330917325,
"min": -1.0000000521540642,
"max": 1.6956217682892734,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 198.0203978717327,
"min": -31.99320164322853,
"max": 198.0203978717327,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.039314790405472345,
"min": 0.039314790405472345,
"max": 12.443137101829052,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.599830477440264,
"min": 4.228846311569214,
"max": 199.09019362926483,
"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": "1674246583",
"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": "1674248597"
},
"total": 2014.3547898529996,
"count": 1,
"self": 0.5938932189992556,
"children": {
"run_training.setup": {
"total": 0.10104661200011833,
"count": 1,
"self": 0.10104661200011833
},
"TrainerController.start_learning": {
"total": 2013.6598500220002,
"count": 1,
"self": 1.1466442419978193,
"children": {
"TrainerController._reset_env": {
"total": 6.02492937299985,
"count": 1,
"self": 6.02492937299985
},
"TrainerController.advance": {
"total": 2006.4049006600026,
"count": 64036,
"self": 1.1629411669359797,
"children": {
"env_step": {
"total": 1378.2410679210134,
"count": 64036,
"self": 1281.4537442290625,
"children": {
"SubprocessEnvManager._take_step": {
"total": 96.06808303598336,
"count": 64036,
"self": 3.9358532850260417,
"children": {
"TorchPolicy.evaluate": {
"total": 92.13222975095732,
"count": 62549,
"self": 31.22985292890644,
"children": {
"TorchPolicy.sample_actions": {
"total": 60.90237682205088,
"count": 62549,
"self": 60.90237682205088
}
}
}
}
},
"workers": {
"total": 0.7192406559674964,
"count": 64036,
"self": 0.0,
"children": {
"worker_root": {
"total": 2010.1277326570025,
"count": 64036,
"is_parallel": true,
"self": 820.4672872051106,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0025227329997505876,
"count": 1,
"is_parallel": true,
"self": 0.000817839999399439,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017048930003511487,
"count": 8,
"is_parallel": true,
"self": 0.0017048930003511487
}
}
},
"UnityEnvironment.step": {
"total": 0.04264872200019454,
"count": 1,
"is_parallel": true,
"self": 0.0004526350003288826,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003988729999946372,
"count": 1,
"is_parallel": true,
"self": 0.0003988729999946372
},
"communicator.exchange": {
"total": 0.040310888000021805,
"count": 1,
"is_parallel": true,
"self": 0.040310888000021805
},
"steps_from_proto": {
"total": 0.001486325999849214,
"count": 1,
"is_parallel": true,
"self": 0.00036543599890137557,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011208900009478384,
"count": 8,
"is_parallel": true,
"self": 0.0011208900009478384
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1189.660445451892,
"count": 64035,
"is_parallel": true,
"self": 26.33586833079835,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 20.719368865034994,
"count": 64035,
"is_parallel": true,
"self": 20.719368865034994
},
"communicator.exchange": {
"total": 1048.7188494520306,
"count": 64035,
"is_parallel": true,
"self": 1048.7188494520306
},
"steps_from_proto": {
"total": 93.88635880402808,
"count": 64035,
"is_parallel": true,
"self": 20.179030496015457,
"children": {
"_process_rank_one_or_two_observation": {
"total": 73.70732830801262,
"count": 512280,
"is_parallel": true,
"self": 73.70732830801262
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 627.0008915720532,
"count": 64036,
"self": 2.16631364200839,
"children": {
"process_trajectory": {
"total": 137.81368184304893,
"count": 64036,
"self": 137.52674460804883,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2869372350000958,
"count": 2,
"self": 0.2869372350000958
}
}
},
"_update_policy": {
"total": 487.0208960869959,
"count": 455,
"self": 182.55447589300366,
"children": {
"TorchPPOOptimizer.update": {
"total": 304.46642019399223,
"count": 22824,
"self": 304.46642019399223
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.779998097452335e-07,
"count": 1,
"self": 8.779998097452335e-07
},
"TrainerController._save_models": {
"total": 0.0833748690001812,
"count": 1,
"self": 0.0014260900006775046,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0819487789995037,
"count": 1,
"self": 0.0819487789995037
}
}
}
}
}
}
}