|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.30878549814224243, |
|
"min": 0.30878549814224243, |
|
"max": 1.4065443277359009, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 9233.921875, |
|
"min": 9233.921875, |
|
"max": 42668.9296875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989983.0, |
|
"min": 29952.0, |
|
"max": 989983.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989983.0, |
|
"min": 29952.0, |
|
"max": 989983.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.6260428428649902, |
|
"min": -0.1239318922162056, |
|
"max": 0.7087668180465698, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 178.42221069335938, |
|
"min": -29.743654251098633, |
|
"max": 201.99855041503906, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.00834602490067482, |
|
"min": -0.03647370636463165, |
|
"max": 0.6505448222160339, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 2.37861704826355, |
|
"min": -10.030269622802734, |
|
"max": 154.1791229248047, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06878873727857318, |
|
"min": 0.0669038255557699, |
|
"max": 0.07362794883090243, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.0318310591785977, |
|
"min": 0.47033216640983455, |
|
"max": 1.0918905346576744, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.016499617166270873, |
|
"min": 0.0010142359632326187, |
|
"max": 0.019295246457944473, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.2474942574940631, |
|
"min": 0.007925119198983432, |
|
"max": 0.2474942574940631, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.453217515626665e-06, |
|
"min": 7.453217515626665e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00011179826273439997, |
|
"min": 0.00011179826273439997, |
|
"max": 0.0035081453306183, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10248437333333335, |
|
"min": 0.10248437333333335, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5372656000000002, |
|
"min": 1.3691136000000002, |
|
"max": 2.5726459000000004, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00025818889599999996, |
|
"min": 0.00025818889599999996, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0038728334399999995, |
|
"min": 0.0038728334399999995, |
|
"max": 0.11696123183, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.017046082764863968, |
|
"min": 0.017046082764863968, |
|
"max": 0.6730450391769409, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.2556912302970886, |
|
"min": 0.2498343139886856, |
|
"max": 4.711315155029297, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 307.6666666666667, |
|
"min": 279.50467289719626, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30459.0, |
|
"min": 15984.0, |
|
"max": 33252.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.6317009940893963, |
|
"min": -1.0000000521540642, |
|
"max": 1.6830953085951716, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 161.53839841485023, |
|
"min": -32.000001668930054, |
|
"max": 180.09119801968336, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.6317009940893963, |
|
"min": -1.0000000521540642, |
|
"max": 1.6830953085951716, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 161.53839841485023, |
|
"min": -32.000001668930054, |
|
"max": 180.09119801968336, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.05351920378179233, |
|
"min": 0.05351920378179233, |
|
"max": 13.652445676038042, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 5.298401174397441, |
|
"min": 5.298401174397441, |
|
"max": 218.43913081660867, |
|
"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": "1679431910", |
|
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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 Training112 --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": "1679434154" |
|
}, |
|
"total": 2243.598298204999, |
|
"count": 1, |
|
"self": 0.4743138329995418, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.10329088599974057, |
|
"count": 1, |
|
"self": 0.10329088599974057 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2243.020693486, |
|
"count": 1, |
|
"self": 1.3411638967854742, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.524614370999188, |
|
"count": 1, |
|
"self": 6.524614370999188 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2235.065435024214, |
|
"count": 64185, |
|
"self": 1.5252545270113842, |
|
"children": { |
|
"env_step": { |
|
"total": 1611.549475112185, |
|
"count": 64185, |
|
"self": 1502.954491310299, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 107.8041905680684, |
|
"count": 64185, |
|
"self": 4.912926397321826, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 102.89126417074658, |
|
"count": 62567, |
|
"self": 102.89126417074658 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.7907932338175669, |
|
"count": 64185, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2238.1158219349154, |
|
"count": 64185, |
|
"is_parallel": true, |
|
"self": 850.2850226768842, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0019085300000369898, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006519950002257247, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012565349998112652, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012565349998112652 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.09338815399951272, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005497140000443324, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004703879994849558, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004703879994849558 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.09047946099963156, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.09047946099963156 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0018885910003518802, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003943149995393469, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0014942760008125333, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0014942760008125333 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1387.8307992580312, |
|
"count": 64184, |
|
"is_parallel": true, |
|
"self": 31.01560196646551, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 23.621474511350243, |
|
"count": 64184, |
|
"is_parallel": true, |
|
"self": 23.621474511350243 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1237.753081751991, |
|
"count": 64184, |
|
"is_parallel": true, |
|
"self": 1237.753081751991 |
|
}, |
|
"steps_from_proto": { |
|
"total": 95.44064102822449, |
|
"count": 64184, |
|
"is_parallel": true, |
|
"self": 20.51449231301467, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 74.92614871520982, |
|
"count": 513472, |
|
"is_parallel": true, |
|
"self": 74.92614871520982 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 621.9907053850175, |
|
"count": 64185, |
|
"self": 2.614478388753014, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 121.5869534382764, |
|
"count": 64185, |
|
"self": 121.32011537627659, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.2668380619998061, |
|
"count": 2, |
|
"self": 0.2668380619998061 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 497.78927355798805, |
|
"count": 451, |
|
"self": 317.8746718512484, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 179.91460170673963, |
|
"count": 22830, |
|
"self": 179.91460170673963 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.880004654405639e-07, |
|
"count": 1, |
|
"self": 9.880004654405639e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08947920600076031, |
|
"count": 1, |
|
"self": 0.001424603000486968, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.08805460300027335, |
|
"count": 1, |
|
"self": 0.08805460300027335 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |