stalaei's picture
First Push
d7af1b2 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.19440071284770966,
"min": 0.19440071284770966,
"max": 1.4442222118377686,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 5878.677734375,
"min": 5861.92578125,
"max": 43811.92578125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989904.0,
"min": 29952.0,
"max": 989904.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989904.0,
"min": 29952.0,
"max": 989904.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4109816551208496,
"min": -0.3011799156665802,
"max": 0.46822142601013184,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 109.32112121582031,
"min": -71.379638671875,
"max": 126.41978454589844,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.017129085958003998,
"min": -0.05301077291369438,
"max": 0.5120681524276733,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 4.556336879730225,
"min": -13.729789733886719,
"max": 121.36014556884766,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06635437856935564,
"min": 0.06463620840714976,
"max": 0.07186235835386377,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9289612999709789,
"min": 0.4936035644817005,
"max": 1.0304104430611272,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.012560052388358773,
"min": 0.0010836837870622472,
"max": 0.014934527065021727,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.1758407334370228,
"min": 0.013004205444746966,
"max": 0.19343438416185296,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.569397476899997e-06,
"min": 7.569397476899997e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010597156467659996,
"min": 0.00010597156467659996,
"max": 0.0033745504751498995,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1025231,
"min": 0.1025231,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4353234000000001,
"min": 1.3886848,
"max": 2.5723732000000004,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026205768999999996,
"min": 0.00026205768999999996,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036688076599999996,
"min": 0.0036688076599999996,
"max": 0.11250252499,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010337711311876774,
"min": 0.010135934688150883,
"max": 0.6702836155891418,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.14472796022891998,
"min": 0.14472796022891998,
"max": 4.691985130310059,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 480.7258064516129,
"min": 398.64864864864865,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29805.0,
"min": 15984.0,
"max": 32677.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4547419132244201,
"min": -1.0000000521540642,
"max": 1.493197274671213,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 90.19399861991405,
"min": -30.708801709115505,
"max": 110.49659832566977,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4547419132244201,
"min": -1.0000000521540642,
"max": 1.493197274671213,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 90.19399861991405,
"min": -30.708801709115505,
"max": 110.49659832566977,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.050635081089680054,
"min": 0.043463232471195455,
"max": 14.030672540422529,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.1393750275601633,
"min": 3.009056891343789,
"max": 224.49076064676046,
"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": "1743193812",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/stalaei/miniconda3/envs/DeepRL/bin/mlagents-learn ./config/ppo/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": "1743195391"
},
"total": 1579.557746342034,
"count": 1,
"self": 0.4747931850142777,
"children": {
"run_training.setup": {
"total": 0.09430073807016015,
"count": 1,
"self": 0.09430073807016015
},
"TrainerController.start_learning": {
"total": 1578.9886524189496,
"count": 1,
"self": 0.8005461359862238,
"children": {
"TrainerController._reset_env": {
"total": 3.758117245975882,
"count": 1,
"self": 3.758117245975882
},
"TrainerController.advance": {
"total": 1574.3338288740488,
"count": 63716,
"self": 0.8441514148144051,
"children": {
"env_step": {
"total": 1081.9391244470607,
"count": 63716,
"self": 981.5161179142306,
"children": {
"SubprocessEnvManager._take_step": {
"total": 99.89560818008613,
"count": 63716,
"self": 2.8839610354043543,
"children": {
"TorchPolicy.evaluate": {
"total": 97.01164714468177,
"count": 62558,
"self": 97.01164714468177
}
}
},
"workers": {
"total": 0.5273983527440578,
"count": 63716,
"self": 0.0,
"children": {
"worker_root": {
"total": 1577.5384196408559,
"count": 63716,
"is_parallel": true,
"self": 661.2633758714655,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017217110143974423,
"count": 1,
"is_parallel": true,
"self": 0.0005022058030590415,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012195052113384008,
"count": 8,
"is_parallel": true,
"self": 0.0012195052113384008
}
}
},
"UnityEnvironment.step": {
"total": 0.03246302390471101,
"count": 1,
"is_parallel": true,
"self": 0.0002855089260265231,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002941190032288432,
"count": 1,
"is_parallel": true,
"self": 0.0002941190032288432
},
"communicator.exchange": {
"total": 0.030994160915724933,
"count": 1,
"is_parallel": true,
"self": 0.030994160915724933
},
"steps_from_proto": {
"total": 0.0008892350597307086,
"count": 1,
"is_parallel": true,
"self": 0.00020726898219436407,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006819660775363445,
"count": 8,
"is_parallel": true,
"self": 0.0006819660775363445
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 916.2750437693903,
"count": 63715,
"is_parallel": true,
"self": 16.90292180608958,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 12.104989214567468,
"count": 63715,
"is_parallel": true,
"self": 12.104989214567468
},
"communicator.exchange": {
"total": 837.4113395578461,
"count": 63715,
"is_parallel": true,
"self": 837.4113395578461
},
"steps_from_proto": {
"total": 49.8557931908872,
"count": 63715,
"is_parallel": true,
"self": 10.543175722006708,
"children": {
"_process_rank_one_or_two_observation": {
"total": 39.31261746888049,
"count": 509720,
"is_parallel": true,
"self": 39.31261746888049
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 491.5505530121736,
"count": 63716,
"self": 1.2868891934631392,
"children": {
"process_trajectory": {
"total": 83.9845936173806,
"count": 63716,
"self": 83.76073053525761,
"children": {
"RLTrainer._checkpoint": {
"total": 0.223863082122989,
"count": 2,
"self": 0.223863082122989
}
}
},
"_update_policy": {
"total": 406.2790702013299,
"count": 451,
"self": 209.59970490413252,
"children": {
"TorchPPOOptimizer.update": {
"total": 196.67936529719736,
"count": 22794,
"self": 196.67936529719736
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.799834176898003e-07,
"count": 1,
"self": 8.799834176898003e-07
},
"TrainerController._save_models": {
"total": 0.09615928295534104,
"count": 1,
"self": 0.0047133719781413674,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09144591097719967,
"count": 1,
"self": 0.09144591097719967
}
}
}
}
}
}
}