|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.3238077461719513, |
|
"min": 0.30464068055152893, |
|
"max": 1.384185552597046, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 9740.13671875, |
|
"min": 9124.59765625, |
|
"max": 41990.65234375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989950.0, |
|
"min": 29952.0, |
|
"max": 989950.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989950.0, |
|
"min": 29952.0, |
|
"max": 989950.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.5838682055473328, |
|
"min": -0.09767741709947586, |
|
"max": 0.6215424537658691, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 163.48309326171875, |
|
"min": -23.149547576904297, |
|
"max": 172.78880310058594, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.029793789610266685, |
|
"min": -0.003969848155975342, |
|
"max": 0.5246034860610962, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 8.34226131439209, |
|
"min": -1.1155273914337158, |
|
"max": 124.33102416992188, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06607722899380385, |
|
"min": 0.06322968994532453, |
|
"max": 0.0752871887250674, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9250812059132538, |
|
"min": 0.5021530170777769, |
|
"max": 1.129307830876011, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.016124860695886086, |
|
"min": 0.0005738098474814362, |
|
"max": 0.018259115102929564, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.22574804974240523, |
|
"min": 0.0063119083222957974, |
|
"max": 0.2482711419773598, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.5734689041142845e-06, |
|
"min": 7.5734689041142845e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010602856465759998, |
|
"min": 0.00010602856465759998, |
|
"max": 0.0036337147887617995, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10252445714285714, |
|
"min": 0.10252445714285714, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4353424, |
|
"min": 1.3886848, |
|
"max": 2.6112382000000003, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002621932685714286, |
|
"min": 0.0002621932685714286, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0036707057600000002, |
|
"min": 0.0036707057600000002, |
|
"max": 0.12114269618, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.049379862844944, |
|
"min": 0.04845596104860306, |
|
"max": 0.7750002145767212, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.6913180947303772, |
|
"min": 0.678383469581604, |
|
"max": 5.425001621246338, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 345.13483146067415, |
|
"min": 308.3707865168539, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30717.0, |
|
"min": 15984.0, |
|
"max": 32908.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.4975055959284975, |
|
"min": -1.0000000521540642, |
|
"max": 1.665387734542696, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 133.27799803763628, |
|
"min": -31.99760165810585, |
|
"max": 163.2079979851842, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.4975055959284975, |
|
"min": -1.0000000521540642, |
|
"max": 1.665387734542696, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 133.27799803763628, |
|
"min": -31.99760165810585, |
|
"max": 163.2079979851842, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.17290613018244433, |
|
"min": 0.16724884639411502, |
|
"max": 16.172629699110985, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 15.388645586237544, |
|
"min": 15.08791030064458, |
|
"max": 258.76207518577576, |
|
"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": "1704005800", |
|
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.1.2+cu121", |
|
"numpy_version": "1.23.5", |
|
"end_time_seconds": "1704008244" |
|
}, |
|
"total": 2443.5232975890003, |
|
"count": 1, |
|
"self": 0.5954386670005078, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.055205353000019386, |
|
"count": 1, |
|
"self": 0.055205353000019386 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2442.872653569, |
|
"count": 1, |
|
"self": 1.9799203779671188, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 2.870515118000185, |
|
"count": 1, |
|
"self": 2.870515118000185 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2437.892613699032, |
|
"count": 63996, |
|
"self": 1.9108032131066466, |
|
"children": { |
|
"env_step": { |
|
"total": 1761.660532516033, |
|
"count": 63996, |
|
"self": 1603.308490314998, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 157.15914342400583, |
|
"count": 63996, |
|
"self": 5.668157140059066, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 151.49098628394677, |
|
"count": 62557, |
|
"self": 151.49098628394677 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 1.1928987770293134, |
|
"count": 63996, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2436.475573560971, |
|
"count": 63996, |
|
"is_parallel": true, |
|
"self": 976.8024616489952, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.001827056000365701, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005591039998762426, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012679520004894584, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012679520004894584 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.07839620400000058, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006100149994381354, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004202600002827239, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004202600002827239 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.07519608100028563, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.07519608100028563 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.00216984799999409, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00035325300041222363, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0018165949995818664, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0018165949995818664 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1459.6731119119759, |
|
"count": 63995, |
|
"is_parallel": true, |
|
"self": 39.519646650917366, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 26.273796364007012, |
|
"count": 63995, |
|
"is_parallel": true, |
|
"self": 26.273796364007012 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1283.8651440250578, |
|
"count": 63995, |
|
"is_parallel": true, |
|
"self": 1283.8651440250578 |
|
}, |
|
"steps_from_proto": { |
|
"total": 110.01452487199367, |
|
"count": 63995, |
|
"is_parallel": true, |
|
"self": 23.71707621517635, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 86.29744865681732, |
|
"count": 511960, |
|
"is_parallel": true, |
|
"self": 86.29744865681732 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 674.3212779698924, |
|
"count": 63996, |
|
"self": 3.6119213008855695, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 137.89328357299382, |
|
"count": 63996, |
|
"self": 137.65331308799387, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.239970484999958, |
|
"count": 2, |
|
"self": 0.239970484999958 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 532.816073096013, |
|
"count": 453, |
|
"self": 315.8378356030812, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 216.97823749293184, |
|
"count": 22788, |
|
"self": 216.97823749293184 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0920002750935964e-06, |
|
"count": 1, |
|
"self": 1.0920002750935964e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.12960328200006188, |
|
"count": 1, |
|
"self": 0.002406681000138633, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.12719660099992325, |
|
"count": 1, |
|
"self": 0.12719660099992325 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |