numan966's picture
Pyramid Training Trial 1
f4b0906
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4086970090866089,
"min": 0.37393656373023987,
"max": 1.46848726272583,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12260.91015625,
"min": 11134.3349609375,
"max": 44548.03125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989944.0,
"min": 29952.0,
"max": 989944.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989944.0,
"min": 29952.0,
"max": 989944.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5412381887435913,
"min": -0.1297784447669983,
"max": 0.5412381887435913,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 149.38174438476562,
"min": -31.27660369873047,
"max": 149.38174438476562,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.008864261209964752,
"min": -0.0039824978448450565,
"max": 0.28299206495285034,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.446536064147949,
"min": -1.0035895109176636,
"max": 67.06912231445312,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07048263885799849,
"min": 0.06735671893905468,
"max": 0.07365917805804027,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9867569440119789,
"min": 0.49417078839788947,
"max": 1.0555722584820115,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01530959817920179,
"min": 0.0008303822317957055,
"max": 0.01644480566633409,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21433437450882506,
"min": 0.005812675622569939,
"max": 0.2466720849950113,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.57826890251429e-06,
"min": 7.57826890251429e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010609576463520005,
"min": 0.00010609576463520005,
"max": 0.0032565363144880007,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10252605714285713,
"min": 0.10252605714285713,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4353647999999999,
"min": 1.3691136000000002,
"max": 2.485512,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002623531085714287,
"min": 0.0002623531085714287,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036729435200000015,
"min": 0.0036729435200000015,
"max": 0.10858264879999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.007962701842188835,
"min": 0.007709507830440998,
"max": 0.3838077485561371,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.11147782951593399,
"min": 0.10793311148881912,
"max": 2.6866543292999268,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 331.75,
"min": 331.75,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 27867.0,
"min": 15984.0,
"max": 33146.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5734505831118089,
"min": -1.0000000521540642,
"max": 1.5796789262247712,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 130.59639839828014,
"min": -32.000001668930054,
"max": 130.59639839828014,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5734505831118089,
"min": -1.0000000521540642,
"max": 1.5796789262247712,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 130.59639839828014,
"min": -32.000001668930054,
"max": 130.59639839828014,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.028093292690842996,
"min": 0.028093292690842996,
"max": 7.462746617384255,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.3317432933399687,
"min": 2.3317432933399687,
"max": 119.40394587814808,
"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": "1673562357",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "1673564412"
},
"total": 2055.3590660460004,
"count": 1,
"self": 0.4797483379998084,
"children": {
"run_training.setup": {
"total": 0.11122113300007186,
"count": 1,
"self": 0.11122113300007186
},
"TrainerController.start_learning": {
"total": 2054.7680965750005,
"count": 1,
"self": 1.2095174111514098,
"children": {
"TrainerController._reset_env": {
"total": 6.781805816000087,
"count": 1,
"self": 6.781805816000087
},
"TrainerController.advance": {
"total": 2046.6848266848488,
"count": 63818,
"self": 1.2997598229558207,
"children": {
"env_step": {
"total": 1382.438376568005,
"count": 63818,
"self": 1280.51574742295,
"children": {
"SubprocessEnvManager._take_step": {
"total": 101.15187044606182,
"count": 63818,
"self": 4.201860144017246,
"children": {
"TorchPolicy.evaluate": {
"total": 96.95001030204457,
"count": 62538,
"self": 32.708206102058284,
"children": {
"TorchPolicy.sample_actions": {
"total": 64.24180419998629,
"count": 62538,
"self": 64.24180419998629
}
}
}
}
},
"workers": {
"total": 0.770758698993177,
"count": 63818,
"self": 0.0,
"children": {
"worker_root": {
"total": 2050.311638637964,
"count": 63818,
"is_parallel": true,
"self": 867.1410949409546,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018635880001056648,
"count": 1,
"is_parallel": true,
"self": 0.000684196000747761,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011793919993579038,
"count": 8,
"is_parallel": true,
"self": 0.0011793919993579038
}
}
},
"UnityEnvironment.step": {
"total": 0.0802953580000576,
"count": 1,
"is_parallel": true,
"self": 0.0005361890002859582,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041444799990131287,
"count": 1,
"is_parallel": true,
"self": 0.00041444799990131287
},
"communicator.exchange": {
"total": 0.07777185899976757,
"count": 1,
"is_parallel": true,
"self": 0.07777185899976757
},
"steps_from_proto": {
"total": 0.0015728620001027593,
"count": 1,
"is_parallel": true,
"self": 0.0003987949994552764,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001174067000647483,
"count": 8,
"is_parallel": true,
"self": 0.001174067000647483
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1183.1705436970092,
"count": 63817,
"is_parallel": true,
"self": 27.999441318870595,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.0337363060562,
"count": 63817,
"is_parallel": true,
"self": 22.0337363060562
},
"communicator.exchange": {
"total": 1033.3226130490557,
"count": 63817,
"is_parallel": true,
"self": 1033.3226130490557
},
"steps_from_proto": {
"total": 99.8147530230267,
"count": 63817,
"is_parallel": true,
"self": 21.774726232104058,
"children": {
"_process_rank_one_or_two_observation": {
"total": 78.04002679092264,
"count": 510536,
"is_parallel": true,
"self": 78.04002679092264
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 662.946690293888,
"count": 63818,
"self": 2.2732369578807265,
"children": {
"process_trajectory": {
"total": 145.57842446901623,
"count": 63818,
"self": 145.3906226750173,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18780179399891495,
"count": 2,
"self": 0.18780179399891495
}
}
},
"_update_policy": {
"total": 515.095028866991,
"count": 444,
"self": 200.8759575758968,
"children": {
"TorchPPOOptimizer.update": {
"total": 314.2190712910942,
"count": 22803,
"self": 314.2190712910942
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.85000042419415e-07,
"count": 1,
"self": 9.85000042419415e-07
},
"TrainerController._save_models": {
"total": 0.09194567800022924,
"count": 1,
"self": 0.001313290000325651,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09063238799990359,
"count": 1,
"self": 0.09063238799990359
}
}
}
}
}
}
}