yogjoshi14's picture
Final Push
2c32250
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 1.0427734851837158,
"min": 0.9910084009170532,
"max": 1.5067851543426514,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 31233.15234375,
"min": 29603.40234375,
"max": 45709.8359375,
"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": -0.0678025484085083,
"min": -0.12691162526607513,
"max": -0.06582409888505936,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -16.40821647644043,
"min": -30.078054428100586,
"max": -15.863608360290527,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.013215010054409504,
"min": 0.005361036863178015,
"max": 0.2298058420419693,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 3.1980323791503906,
"min": 1.2973709106445312,
"max": 54.965309143066406,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06827791020370685,
"min": 0.06472473532565118,
"max": 0.07365896658642877,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9558907428518959,
"min": 0.4530731472795583,
"max": 1.0312255322100028,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.0021780173987101556,
"min": 0.00018092140639065015,
"max": 0.005838643023404681,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.030492243581942177,
"min": 0.002532899689469102,
"max": 0.04087050116383277,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.720059984000006e-07,
"min": 7.720059984000006e-07,
"max": 2.95150644736e-05,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 1.0808083977600009e-05,
"min": 1.0808083977600009e-05,
"max": 0.00031364185452800004,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10257302857142858,
"min": 0.10257302857142858,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4360224000000001,
"min": 1.3691136000000002,
"max": 2.345472,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026704555428571454,
"min": 0.00026704555428571454,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0037386377600000034,
"min": 0.0037386377600000034,
"max": 0.1045726528,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.011356151662766933,
"min": 0.011008656583726406,
"max": 0.2891857624053955,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.15898612141609192,
"min": 0.15412119030952454,
"max": 2.0243003368377686,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 973.53125,
"min": 941.3666666666667,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31153.0,
"min": 15984.0,
"max": 32174.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.6615500550251454,
"min": -1.0000000521540642,
"max": -0.6086667145291964,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -21.169601760804653,
"min": -32.000001668930054,
"max": -16.000000834465027,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.6615500550251454,
"min": -1.0000000521540642,
"max": -0.6086667145291964,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -21.169601760804653,
"min": -32.000001668930054,
"max": -16.000000834465027,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.11294995617936365,
"min": 0.1112391704580549,
"max": 5.6130590392276645,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.614398597739637,
"min": 3.195283649954945,
"max": 89.80894462764263,
"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": "1691758550",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1691760540"
},
"total": 1990.1451167470002,
"count": 1,
"self": 0.4857567509998262,
"children": {
"run_training.setup": {
"total": 0.03768296300017937,
"count": 1,
"self": 0.03768296300017937
},
"TrainerController.start_learning": {
"total": 1989.6216770330002,
"count": 1,
"self": 1.3366268709655742,
"children": {
"TrainerController._reset_env": {
"total": 4.0180048360000455,
"count": 1,
"self": 4.0180048360000455
},
"TrainerController.advance": {
"total": 1984.1709402170347,
"count": 63033,
"self": 1.3382812060538072,
"children": {
"env_step": {
"total": 1326.792135909967,
"count": 63033,
"self": 1218.4401755140289,
"children": {
"SubprocessEnvManager._take_step": {
"total": 107.55894720799142,
"count": 63033,
"self": 4.583389198972327,
"children": {
"TorchPolicy.evaluate": {
"total": 102.9755580090191,
"count": 62566,
"self": 102.9755580090191
}
}
},
"workers": {
"total": 0.7930131879468263,
"count": 63033,
"self": 0.0,
"children": {
"worker_root": {
"total": 1984.979651430895,
"count": 63033,
"is_parallel": true,
"self": 876.5292086808956,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017883699999856617,
"count": 1,
"is_parallel": true,
"self": 0.0005463630002395803,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012420069997460814,
"count": 8,
"is_parallel": true,
"self": 0.0012420069997460814
}
}
},
"UnityEnvironment.step": {
"total": 0.04749794999997903,
"count": 1,
"is_parallel": true,
"self": 0.0005397270003868471,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004672799998388655,
"count": 1,
"is_parallel": true,
"self": 0.0004672799998388655
},
"communicator.exchange": {
"total": 0.044588652999891565,
"count": 1,
"is_parallel": true,
"self": 0.044588652999891565
},
"steps_from_proto": {
"total": 0.0019022899998617504,
"count": 1,
"is_parallel": true,
"self": 0.0003758419995847362,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015264480002770142,
"count": 8,
"is_parallel": true,
"self": 0.0015264480002770142
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1108.4504427499994,
"count": 63032,
"is_parallel": true,
"self": 33.27731592390137,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.97135936708787,
"count": 63032,
"is_parallel": true,
"self": 22.97135936708787
},
"communicator.exchange": {
"total": 949.1294334070049,
"count": 63032,
"is_parallel": true,
"self": 949.1294334070049
},
"steps_from_proto": {
"total": 103.07233405200532,
"count": 63032,
"is_parallel": true,
"self": 20.10559141985982,
"children": {
"_process_rank_one_or_two_observation": {
"total": 82.9667426321455,
"count": 504256,
"is_parallel": true,
"self": 82.9667426321455
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 656.0405231010138,
"count": 63033,
"self": 2.2702460239677293,
"children": {
"process_trajectory": {
"total": 107.7271595220484,
"count": 63033,
"self": 107.52157427804809,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20558524400030365,
"count": 2,
"self": 0.20558524400030365
}
}
},
"_update_policy": {
"total": 546.0431175549977,
"count": 430,
"self": 356.2182041680046,
"children": {
"TorchPPOOptimizer.update": {
"total": 189.8249133869931,
"count": 22893,
"self": 189.8249133869931
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.469999895372894e-07,
"count": 1,
"self": 9.469999895372894e-07
},
"TrainerController._save_models": {
"total": 0.09610416199984684,
"count": 1,
"self": 0.0013532489997487573,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09475091300009808,
"count": 1,
"self": 0.09475091300009808
}
}
}
}
}
}
}