|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.4371541738510132, |
|
"min": 0.4371541738510132, |
|
"max": 1.447709321975708, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 13177.5751953125, |
|
"min": 13177.5751953125, |
|
"max": 43917.7109375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989934.0, |
|
"min": 29952.0, |
|
"max": 989934.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989934.0, |
|
"min": 29952.0, |
|
"max": 989934.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.3904217481613159, |
|
"min": -0.11730703711509705, |
|
"max": 0.4008304178714752, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 104.63302612304688, |
|
"min": -28.153688430786133, |
|
"max": 107.02172088623047, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.007560729049146175, |
|
"min": 0.007560729049146175, |
|
"max": 0.2903762757778168, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 2.026275396347046, |
|
"min": 2.026275396347046, |
|
"max": 69.98068237304688, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06818356998943878, |
|
"min": 0.06476537082620658, |
|
"max": 0.0744347085179912, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.954569979852143, |
|
"min": 0.5210429596259384, |
|
"max": 1.0629619741036247, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.012574989494515604, |
|
"min": 0.0002667785270070738, |
|
"max": 0.013609561172779647, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.17604985292321845, |
|
"min": 0.0032013423240848855, |
|
"max": 0.20414341759169471, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.392054678871431e-06, |
|
"min": 7.392054678871431e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010348876550420004, |
|
"min": 0.00010348876550420004, |
|
"max": 0.003490864636378499, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10246398571428572, |
|
"min": 0.10246398571428572, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4344958, |
|
"min": 1.3886848, |
|
"max": 2.5275128000000002, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00025615217285714293, |
|
"min": 0.00025615217285714293, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0035861304200000012, |
|
"min": 0.0035861304200000012, |
|
"max": 0.11637578784999998, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.01095340121537447, |
|
"min": 0.010662509128451347, |
|
"max": 0.45290905237197876, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.15334761142730713, |
|
"min": 0.14927512407302856, |
|
"max": 3.170363426208496, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 445.030303030303, |
|
"min": 445.030303030303, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29372.0, |
|
"min": 15984.0, |
|
"max": 34032.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.4640363398374934, |
|
"min": -1.0000000521540642, |
|
"max": 1.4640363398374934, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 96.62639842927456, |
|
"min": -31.996801674365997, |
|
"max": 96.62639842927456, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.4640363398374934, |
|
"min": -1.0000000521540642, |
|
"max": 1.4640363398374934, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 96.62639842927456, |
|
"min": -31.996801674365997, |
|
"max": 96.62639842927456, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.05050653808222816, |
|
"min": 0.04970219661312961, |
|
"max": 9.314574934542179, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.3334315134270582, |
|
"min": 3.2879879637039267, |
|
"max": 149.03319895267487, |
|
"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": "1685868074", |
|
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", |
|
"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": "1685870278" |
|
}, |
|
"total": 2204.057395255, |
|
"count": 1, |
|
"self": 0.48653779999995095, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.04233597600000394, |
|
"count": 1, |
|
"self": 0.04233597600000394 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2203.528521479, |
|
"count": 1, |
|
"self": 1.3498361630158797, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 3.9726607259999582, |
|
"count": 1, |
|
"self": 3.9726607259999582 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2198.1121879879843, |
|
"count": 63476, |
|
"self": 1.28326596901843, |
|
"children": { |
|
"env_step": { |
|
"total": 1572.7254380020097, |
|
"count": 63476, |
|
"self": 1469.1050416180094, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 102.84468383901151, |
|
"count": 63476, |
|
"self": 4.667240634010511, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 98.177443205001, |
|
"count": 62558, |
|
"self": 98.177443205001 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.7757125449888349, |
|
"count": 63476, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2198.730133192004, |
|
"count": 63476, |
|
"is_parallel": true, |
|
"self": 839.3724559900386, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.005159686000013153, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.003764543999864145, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013951420001490078, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013951420001490078 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.054857802000015, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005523090001133824, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005269149999662659, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005269149999662659 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.05176073899997391, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.05176073899997391 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.002017838999961441, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004486429999133179, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001569196000048123, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001569196000048123 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1359.3576772019653, |
|
"count": 63475, |
|
"is_parallel": true, |
|
"self": 31.780383560045266, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 22.730661344931377, |
|
"count": 63475, |
|
"is_parallel": true, |
|
"self": 22.730661344931377 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1208.2888097170128, |
|
"count": 63475, |
|
"is_parallel": true, |
|
"self": 1208.2888097170128 |
|
}, |
|
"steps_from_proto": { |
|
"total": 96.55782257997589, |
|
"count": 63475, |
|
"is_parallel": true, |
|
"self": 19.49321567102595, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 77.06460690894994, |
|
"count": 507800, |
|
"is_parallel": true, |
|
"self": 77.06460690894994 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 624.1034840169561, |
|
"count": 63476, |
|
"self": 2.4450470079584647, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 104.43148108800216, |
|
"count": 63476, |
|
"self": 104.16413178700242, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.2673493009997401, |
|
"count": 2, |
|
"self": 0.2673493009997401 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 517.2269559209956, |
|
"count": 449, |
|
"self": 335.0815561780138, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 182.1453997429818, |
|
"count": 22797, |
|
"self": 182.1453997429818 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.179998414765578e-07, |
|
"count": 1, |
|
"self": 9.179998414765578e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09383568400016884, |
|
"count": 1, |
|
"self": 0.0014840770004411752, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09235160699972766, |
|
"count": 1, |
|
"self": 0.09235160699972766 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |