|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.18549159169197083, |
|
"min": 0.16501900553703308, |
|
"max": 1.4877912998199463, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 5514.2939453125, |
|
"min": 4918.88671875, |
|
"max": 45133.63671875, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 2999986.0, |
|
"min": 29952.0, |
|
"max": 2999986.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 2999986.0, |
|
"min": 29952.0, |
|
"max": 2999986.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.8491765260696411, |
|
"min": -0.16802190244197845, |
|
"max": 0.8910682797431946, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 258.149658203125, |
|
"min": -39.821189880371094, |
|
"max": 278.0133056640625, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.002368563786149025, |
|
"min": -0.010633742436766624, |
|
"max": 0.4445153772830963, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 0.720043420791626, |
|
"min": -3.317727565765381, |
|
"max": 105.35014343261719, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06774280974960198, |
|
"min": 0.063515446266614, |
|
"max": 0.07441755345303698, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9483993364944276, |
|
"min": 0.5209228741712588, |
|
"max": 1.0731008608903116, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.015869215046959217, |
|
"min": 0.00018658240380568724, |
|
"max": 0.016393833552553718, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.22216901065742906, |
|
"min": 0.002425571249473934, |
|
"max": 0.22951366973575205, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 1.4967637868261916e-06, |
|
"min": 1.4967637868261916e-06, |
|
"max": 0.00029838354339596195, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 2.0954693015566682e-05, |
|
"min": 2.0954693015566682e-05, |
|
"max": 0.004011072962975699, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10049888809523812, |
|
"min": 0.10049888809523812, |
|
"max": 0.19946118095238097, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4069844333333337, |
|
"min": 1.3962282666666668, |
|
"max": 2.7374939000000005, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 5.983892071428576e-05, |
|
"min": 5.983892071428576e-05, |
|
"max": 0.009946171977142856, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0008377448900000006, |
|
"min": 0.0008377448900000006, |
|
"max": 0.13370872757000002, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.006374638061970472, |
|
"min": 0.0059983269311487675, |
|
"max": 0.5016703009605408, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.08924493193626404, |
|
"min": 0.08397657424211502, |
|
"max": 3.5116920471191406, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 210.52083333333334, |
|
"min": 198.3046357615894, |
|
"max": 999.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30315.0, |
|
"min": 15984.0, |
|
"max": 32538.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.7615020881061787, |
|
"min": -1.0000000521540642, |
|
"max": 1.7970890263988548, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 251.89479859918356, |
|
"min": -29.996201567351818, |
|
"max": 268.15519765019417, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.7615020881061787, |
|
"min": -1.0000000521540642, |
|
"max": 1.7970890263988548, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 251.89479859918356, |
|
"min": -29.996201567351818, |
|
"max": 268.15519765019417, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.014017653583507851, |
|
"min": 0.012781343650102726, |
|
"max": 10.748835414648056, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.0045244624416227, |
|
"min": 1.8405134856147924, |
|
"max": 171.9813666343689, |
|
"count": 100 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 100 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1657570910", |
|
"python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-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": "1657577491" |
|
}, |
|
"total": 6581.106113971001, |
|
"count": 1, |
|
"self": 0.4372175070011508, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.04052239399993596, |
|
"count": 1, |
|
"self": 0.04052239399993596 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 6580.62837407, |
|
"count": 1, |
|
"self": 4.034038596162645, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 9.61948098899984, |
|
"count": 1, |
|
"self": 9.61948098899984 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 6566.880816513838, |
|
"count": 195480, |
|
"self": 4.289930104000632, |
|
"children": { |
|
"env_step": { |
|
"total": 4432.43372245399, |
|
"count": 195480, |
|
"self": 4121.725324592711, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 308.59892481496786, |
|
"count": 195480, |
|
"self": 13.548583634909392, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 295.05034118005847, |
|
"count": 187549, |
|
"self": 101.87077117030117, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 193.1795700097573, |
|
"count": 187549, |
|
"self": 193.1795700097573 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 2.1094730463109954, |
|
"count": 195480, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 6569.793024105923, |
|
"count": 195480, |
|
"is_parallel": true, |
|
"self": 2740.6610778758145, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.005194442999936655, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.003949753999904715, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.00124468900003194, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.00124468900003194 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04604754000001776, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005065469999863126, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004288699999506207, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004288699999506207 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04345994899995276, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04345994899995276 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0016521740001280705, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00042566400020405126, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012265099999240192, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012265099999240192 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 3829.1319462301085, |
|
"count": 195479, |
|
"is_parallel": true, |
|
"self": 82.57355704394695, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 67.52475922283043, |
|
"count": 195479, |
|
"is_parallel": true, |
|
"self": 67.52475922283043 |
|
}, |
|
"communicator.exchange": { |
|
"total": 3404.435974938121, |
|
"count": 195479, |
|
"is_parallel": true, |
|
"self": 3404.435974938121 |
|
}, |
|
"steps_from_proto": { |
|
"total": 274.5976550252101, |
|
"count": 195479, |
|
"is_parallel": true, |
|
"self": 67.90889252627176, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 206.68876249893833, |
|
"count": 1563832, |
|
"is_parallel": true, |
|
"self": 206.68876249893833 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 2130.157163955847, |
|
"count": 195480, |
|
"self": 7.822217081870349, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 495.59853101397266, |
|
"count": 195480, |
|
"self": 495.02613327397285, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.5723977399998148, |
|
"count": 6, |
|
"self": 0.5723977399998148 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1626.736415860004, |
|
"count": 1400, |
|
"self": 643.8071453301063, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 982.9292705298976, |
|
"count": 68376, |
|
"self": 982.9292705298976 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.1539996194187552e-06, |
|
"count": 1, |
|
"self": 1.1539996194187552e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09403681699950539, |
|
"count": 1, |
|
"self": 0.0017135369998868555, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09232327999961853, |
|
"count": 1, |
|
"self": 0.09232327999961853 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |