salohiddin94's picture
Second Push
32766a5
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.40317001938819885,
"min": 0.40317001938819885,
"max": 1.4481173753738403,
"count": 35
},
"Pyramids.Policy.Entropy.sum": {
"value": 12127.3544921875,
"min": 12075.13671875,
"max": 43930.08984375,
"count": 35
},
"Pyramids.Step.mean": {
"value": 1049966.0,
"min": 29952.0,
"max": 1049966.0,
"count": 35
},
"Pyramids.Step.sum": {
"value": 1049966.0,
"min": 29952.0,
"max": 1049966.0,
"count": 35
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6706457138061523,
"min": -0.09748467057943344,
"max": 0.6706457138061523,
"count": 35
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 187.78079223632812,
"min": -23.493804931640625,
"max": 188.60037231445312,
"count": 35
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.016291502863168716,
"min": -0.003944861236959696,
"max": 0.4659078121185303,
"count": 35
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 4.561620712280273,
"min": -1.0808919668197632,
"max": 110.42015075683594,
"count": 35
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06910521153172122,
"min": 0.06449084293022418,
"max": 0.07343877376471449,
"count": 35
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9674729614440971,
"min": 0.48829235371748175,
"max": 1.0439745573482164,
"count": 35
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01332081647290449,
"min": 0.000523297519949862,
"max": 0.0168580547240304,
"count": 35
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.18649143062066287,
"min": 0.006802867759348206,
"max": 0.252870820860456,
"count": 35
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.00019646806308208574,
"min": 0.00019646806308208574,
"max": 0.00029838354339596195,
"count": 35
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0027505528831492003,
"min": 0.0020691136102954665,
"max": 0.0038847071050976656,
"count": 35
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.16548934285714287,
"min": 0.16548934285714287,
"max": 0.19946118095238097,
"count": 35
},
"Pyramids.Policy.Epsilon.sum": {
"value": 2.3168508,
"min": 1.3897045333333333,
"max": 2.782447533333333,
"count": 35
},
"Pyramids.Policy.Beta.mean": {
"value": 0.006552385351428572,
"min": 0.006552385351428572,
"max": 0.009946171977142856,
"count": 35
},
"Pyramids.Policy.Beta.sum": {
"value": 0.09173339492,
"min": 0.06897148288,
"max": 0.12950074309999998,
"count": 35
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010192937217652798,
"min": 0.010192937217652798,
"max": 0.5106141567230225,
"count": 35
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.14270111918449402,
"min": 0.14270111918449402,
"max": 3.5742990970611572,
"count": 35
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 306.47,
"min": 292.90384615384613,
"max": 999.0,
"count": 35
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30647.0,
"min": 15984.0,
"max": 33570.0,
"count": 35
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5935059739649295,
"min": -1.0000000521540642,
"max": 1.6655175026851832,
"count": 35
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 159.35059739649296,
"min": -32.000001668930054,
"max": 171.5355990678072,
"count": 35
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5935059739649295,
"min": -1.0000000521540642,
"max": 1.6655175026851832,
"count": 35
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 159.35059739649296,
"min": -32.000001668930054,
"max": 171.5355990678072,
"count": 35
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03224210243075504,
"min": 0.03224210243075504,
"max": 9.937377551570535,
"count": 35
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.224210243075504,
"min": 3.2001269015599973,
"max": 158.99804082512856,
"count": 35
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 35
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 35
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1697347260",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.0.1+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1697349576"
},
"total": 2316.354977578,
"count": 1,
"self": 0.5469430160001139,
"children": {
"run_training.setup": {
"total": 0.04857531199991172,
"count": 1,
"self": 0.04857531199991172
},
"TrainerController.start_learning": {
"total": 2315.75945925,
"count": 1,
"self": 1.3294142960853605,
"children": {
"TrainerController._reset_env": {
"total": 3.177942450000046,
"count": 1,
"self": 3.177942450000046
},
"TrainerController.advance": {
"total": 2310.9847618069152,
"count": 67792,
"self": 1.45278866185663,
"children": {
"env_step": {
"total": 1652.9108310190236,
"count": 67792,
"self": 1523.9423317840055,
"children": {
"SubprocessEnvManager._take_step": {
"total": 128.148852875986,
"count": 67792,
"self": 4.810697161953158,
"children": {
"TorchPolicy.evaluate": {
"total": 123.33815571403284,
"count": 66427,
"self": 123.33815571403284
}
}
},
"workers": {
"total": 0.8196463590320491,
"count": 67791,
"self": 0.0,
"children": {
"worker_root": {
"total": 2310.907041381049,
"count": 67791,
"is_parallel": true,
"self": 906.6054394521414,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00181001600003583,
"count": 1,
"is_parallel": true,
"self": 0.0005794380001589161,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001230577999876914,
"count": 8,
"is_parallel": true,
"self": 0.001230577999876914
}
}
},
"UnityEnvironment.step": {
"total": 0.0820148530001461,
"count": 1,
"is_parallel": true,
"self": 0.0006666460003543762,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005015879999064055,
"count": 1,
"is_parallel": true,
"self": 0.0005015879999064055
},
"communicator.exchange": {
"total": 0.0792485869999382,
"count": 1,
"is_parallel": true,
"self": 0.0792485869999382
},
"steps_from_proto": {
"total": 0.0015980319999471249,
"count": 1,
"is_parallel": true,
"self": 0.00035363399956622743,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012443980003808974,
"count": 8,
"is_parallel": true,
"self": 0.0012443980003808974
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1404.3016019289078,
"count": 67790,
"is_parallel": true,
"self": 36.4765838598571,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 25.280521432007163,
"count": 67790,
"is_parallel": true,
"self": 25.280521432007163
},
"communicator.exchange": {
"total": 1240.3303210780152,
"count": 67790,
"is_parallel": true,
"self": 1240.3303210780152
},
"steps_from_proto": {
"total": 102.21417555902826,
"count": 67790,
"is_parallel": true,
"self": 20.04974665196687,
"children": {
"_process_rank_one_or_two_observation": {
"total": 82.16442890706139,
"count": 542320,
"is_parallel": true,
"self": 82.16442890706139
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 656.621142126035,
"count": 67791,
"self": 2.5685779291229665,
"children": {
"process_trajectory": {
"total": 124.23307564991546,
"count": 67791,
"self": 124.01369221991581,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21938342999965244,
"count": 2,
"self": 0.21938342999965244
}
}
},
"_update_policy": {
"total": 529.8194885469966,
"count": 475,
"self": 316.783396169993,
"children": {
"TorchPPOOptimizer.update": {
"total": 213.03609237700357,
"count": 24252,
"self": 213.03609237700357
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.7519996617920697e-06,
"count": 1,
"self": 1.7519996617920697e-06
},
"TrainerController._save_models": {
"total": 0.2673389449996648,
"count": 1,
"self": 0.0018464169997969293,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2654925279998679,
"count": 1,
"self": 0.2654925279998679
}
}
}
}
}
}
}