zlicastro's picture
Initial training of PyramidsRND
207886f
raw
history blame
19.2 kB
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3503981828689575,
"min": 0.33831101655960083,
"max": 1.4676374197006226,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 10500.732421875,
"min": 10089.7880859375,
"max": 44522.25,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989993.0,
"min": 29952.0,
"max": 989993.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989993.0,
"min": 29952.0,
"max": 989993.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.2350252866744995,
"min": -0.11902213841676712,
"max": 0.25301042199134827,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 60.166473388671875,
"min": -28.684335708618164,
"max": 65.27668762207031,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.0020303186029195786,
"min": -0.004909656010568142,
"max": 0.3783019483089447,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -0.5197615623474121,
"min": -1.2568719387054443,
"max": 90.79246520996094,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06984950069870267,
"min": 0.06428549473431694,
"max": 0.07280605916249831,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9778930097818375,
"min": 0.48189595578895383,
"max": 1.062486666041271,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.011257555484570775,
"min": 0.0006217175147568319,
"max": 0.011622723999719939,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.15760577678399085,
"min": 0.00795531171594518,
"max": 0.16271813599607915,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.5719474760499946e-06,
"min": 7.5719474760499946e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010600726466469992,
"min": 0.00010600726466469992,
"max": 0.0035076176307942,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10252395000000003,
"min": 0.10252395000000003,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4353353000000004,
"min": 1.3691136000000002,
"max": 2.5692057999999998,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026214260499999984,
"min": 0.00026214260499999984,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003669996469999998,
"min": 0.003669996469999998,
"max": 0.11694365942000003,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.011383293196558952,
"min": 0.011383293196558952,
"max": 0.5018137693405151,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.15936610102653503,
"min": 0.15936610102653503,
"max": 3.5126965045928955,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 624.7659574468086,
"min": 580.1764705882352,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29364.0,
"min": 15984.0,
"max": 32277.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.9495106047772347,
"min": -1.0000000521540642,
"max": 1.022015058628793,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 44.62699842453003,
"min": -32.000001668930054,
"max": 54.16679810732603,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.9495106047772347,
"min": -1.0000000521540642,
"max": 1.022015058628793,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 44.62699842453003,
"min": -32.000001668930054,
"max": 54.16679810732603,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.07597507688370435,
"min": 0.07578566410651832,
"max": 10.158724728040397,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.570828613534104,
"min": 3.570828613534104,
"max": 162.53959564864635,
"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": "1675730815",
"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": "1675732972"
},
"total": 2157.401544096,
"count": 1,
"self": 0.579582221000237,
"children": {
"run_training.setup": {
"total": 0.11509591200001523,
"count": 1,
"self": 0.11509591200001523
},
"TrainerController.start_learning": {
"total": 2156.706865963,
"count": 1,
"self": 1.321353142031512,
"children": {
"TrainerController._reset_env": {
"total": 7.039679187000047,
"count": 1,
"self": 7.039679187000047
},
"TrainerController.advance": {
"total": 2148.253876089969,
"count": 63370,
"self": 1.4239623400708297,
"children": {
"env_step": {
"total": 1381.4182435538828,
"count": 63370,
"self": 1266.6364761639416,
"children": {
"SubprocessEnvManager._take_step": {
"total": 113.96366986799262,
"count": 63370,
"self": 4.593389319979906,
"children": {
"TorchPolicy.evaluate": {
"total": 109.37028054801272,
"count": 62563,
"self": 36.58202471900745,
"children": {
"TorchPolicy.sample_actions": {
"total": 72.78825582900527,
"count": 62563,
"self": 72.78825582900527
}
}
}
}
},
"workers": {
"total": 0.81809752194863,
"count": 63370,
"self": 0.0,
"children": {
"worker_root": {
"total": 2151.9815487950295,
"count": 63370,
"is_parallel": true,
"self": 1000.0741694811197,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017708289999518456,
"count": 1,
"is_parallel": true,
"self": 0.0006551760004640528,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011156529994877928,
"count": 8,
"is_parallel": true,
"self": 0.0011156529994877928
}
}
},
"UnityEnvironment.step": {
"total": 0.045814292999921236,
"count": 1,
"is_parallel": true,
"self": 0.0005124009999235568,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000459576999901401,
"count": 1,
"is_parallel": true,
"self": 0.000459576999901401
},
"communicator.exchange": {
"total": 0.04324898100003338,
"count": 1,
"is_parallel": true,
"self": 0.04324898100003338
},
"steps_from_proto": {
"total": 0.001593334000062896,
"count": 1,
"is_parallel": true,
"self": 0.0004010339998785639,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001192300000184332,
"count": 8,
"is_parallel": true,
"self": 0.001192300000184332
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1151.9073793139098,
"count": 63369,
"is_parallel": true,
"self": 30.701678753838905,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.678793916002405,
"count": 63369,
"is_parallel": true,
"self": 22.678793916002405
},
"communicator.exchange": {
"total": 999.5533238980556,
"count": 63369,
"is_parallel": true,
"self": 999.5533238980556
},
"steps_from_proto": {
"total": 98.97358274601288,
"count": 63369,
"is_parallel": true,
"self": 21.69274512414063,
"children": {
"_process_rank_one_or_two_observation": {
"total": 77.28083762187225,
"count": 506952,
"is_parallel": true,
"self": 77.28083762187225
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 765.4116701960154,
"count": 63370,
"self": 2.6266319230153385,
"children": {
"process_trajectory": {
"total": 163.0090405660019,
"count": 63370,
"self": 162.82367321000197,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18536735599991516,
"count": 2,
"self": 0.18536735599991516
}
}
},
"_update_policy": {
"total": 599.7759977069982,
"count": 446,
"self": 234.2060273630184,
"children": {
"TorchPPOOptimizer.update": {
"total": 365.5699703439798,
"count": 22824,
"self": 365.5699703439798
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.229997885995544e-07,
"count": 1,
"self": 9.229997885995544e-07
},
"TrainerController._save_models": {
"total": 0.09195662100000845,
"count": 1,
"self": 0.0014945900002203416,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09046203099978811,
"count": 1,
"self": 0.09046203099978811
}
}
}
}
}
}
}