|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.3236592411994934, |
|
"min": 0.31995895504951477, |
|
"max": 1.3804181814193726, |
|
"count": 52 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 9683.884765625, |
|
"min": 9506.6201171875, |
|
"max": 41876.3671875, |
|
"count": 52 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 1559957.0, |
|
"min": 29952.0, |
|
"max": 1559957.0, |
|
"count": 52 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 1559957.0, |
|
"min": 29952.0, |
|
"max": 1559957.0, |
|
"count": 52 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.8009302616119385, |
|
"min": -0.09742318838834763, |
|
"max": 0.8087341785430908, |
|
"count": 52 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 233.87164306640625, |
|
"min": -23.38156509399414, |
|
"max": 244.2377166748047, |
|
"count": 52 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.0003482537576928735, |
|
"min": -0.03078695759177208, |
|
"max": 0.37484097480773926, |
|
"count": 52 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 0.10169009864330292, |
|
"min": -8.74349594116211, |
|
"max": 88.83731079101562, |
|
"count": 52 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06909934650632618, |
|
"min": 0.06641634348073108, |
|
"max": 0.07306884105748715, |
|
"count": 52 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9673908510885666, |
|
"min": 0.47176336469219043, |
|
"max": 1.0664764575143206, |
|
"count": 52 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.012188718730439653, |
|
"min": 0.00019509648938030314, |
|
"max": 0.01527911775753767, |
|
"count": 52 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.17064206222615513, |
|
"min": 0.002536254361943941, |
|
"max": 0.21390764860552738, |
|
"count": 52 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 0.00014556713004906905, |
|
"min": 0.00014556713004906905, |
|
"max": 0.00029838354339596195, |
|
"count": 52 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.0020379398206869666, |
|
"min": 0.0020379398206869666, |
|
"max": 0.0038427845190718663, |
|
"count": 52 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.14852235952380952, |
|
"min": 0.14852235952380952, |
|
"max": 0.19946118095238097, |
|
"count": 52 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 2.0793130333333334, |
|
"min": 1.3962282666666668, |
|
"max": 2.767491266666667, |
|
"count": 52 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.004857383716428572, |
|
"min": 0.004857383716428572, |
|
"max": 0.009946171977142856, |
|
"count": 52 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.06800337203000001, |
|
"min": 0.06800337203000001, |
|
"max": 0.12810472052, |
|
"count": 52 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.00605732062831521, |
|
"min": 0.005942605435848236, |
|
"max": 0.4936694800853729, |
|
"count": 52 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.08480248600244522, |
|
"min": 0.0831964761018753, |
|
"max": 3.455686330795288, |
|
"count": 52 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 237.98333333333332, |
|
"min": 231.1451612903226, |
|
"max": 999.0, |
|
"count": 52 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 28558.0, |
|
"min": 15984.0, |
|
"max": 33332.0, |
|
"count": 52 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.7618760199339922, |
|
"min": -1.0000000521540642, |
|
"max": 1.768854827890473, |
|
"count": 52 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 213.18699841201305, |
|
"min": -31.995201662182808, |
|
"max": 223.49099791795015, |
|
"count": 52 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.7618760199339922, |
|
"min": -1.0000000521540642, |
|
"max": 1.768854827890473, |
|
"count": 52 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 213.18699841201305, |
|
"min": -31.995201662182808, |
|
"max": 223.49099791795015, |
|
"count": 52 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.01529563271776342, |
|
"min": 0.01529563271776342, |
|
"max": 10.223189648240805, |
|
"count": 52 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 1.8507715588493738, |
|
"min": 1.8470768433471676, |
|
"max": 163.57103437185287, |
|
"count": 52 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 52 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 52 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1678910463", |
|
"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 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": "1678915948" |
|
}, |
|
"total": 5485.102352989999, |
|
"count": 1, |
|
"self": 0.6813879429992085, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.1417197219998343, |
|
"count": 1, |
|
"self": 0.1417197219998343 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 5484.279245325, |
|
"count": 1, |
|
"self": 3.703674904444597, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 4.320587345000604, |
|
"count": 1, |
|
"self": 4.320587345000604 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 5476.080144606557, |
|
"count": 102292, |
|
"self": 3.9171571713632147, |
|
"children": { |
|
"env_step": { |
|
"total": 3705.149352992212, |
|
"count": 102292, |
|
"self": 3483.2920734153404, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 219.5124774399137, |
|
"count": 102292, |
|
"self": 11.201043181738896, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 208.3114342581748, |
|
"count": 99048, |
|
"self": 208.3114342581748 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 2.3448021369576963, |
|
"count": 102291, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 5472.538342261794, |
|
"count": 102291, |
|
"is_parallel": true, |
|
"self": 2270.499509283867, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0027955379991908558, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0009510059971944429, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0018445320019964129, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0018445320019964129 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.06343255399951886, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006612509996557492, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005331409993232228, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005331409993232228 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.06008661100077006, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.06008661100077006 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0021515509997698246, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004731979997814051, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0016783529999884195, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0016783529999884195 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 3202.038832977927, |
|
"count": 102290, |
|
"is_parallel": true, |
|
"self": 68.86226591511513, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 41.04949926395693, |
|
"count": 102290, |
|
"is_parallel": true, |
|
"self": 41.04949926395693 |
|
}, |
|
"communicator.exchange": { |
|
"total": 2886.3831351125964, |
|
"count": 102290, |
|
"is_parallel": true, |
|
"self": 2886.3831351125964 |
|
}, |
|
"steps_from_proto": { |
|
"total": 205.74393268625863, |
|
"count": 102290, |
|
"is_parallel": true, |
|
"self": 47.31556353067117, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 158.42836915558746, |
|
"count": 818320, |
|
"is_parallel": true, |
|
"self": 158.42836915558746 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 1767.013634442982, |
|
"count": 102291, |
|
"self": 7.242888563813722, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 252.20586099115735, |
|
"count": 102291, |
|
"self": 251.7923840211579, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.4134769699994649, |
|
"count": 3, |
|
"self": 0.4134769699994649 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1507.564884888011, |
|
"count": 725, |
|
"self": 624.359065966064, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 883.205818921947, |
|
"count": 36087, |
|
"self": 883.205818921947 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.9139988580718637e-06, |
|
"count": 1, |
|
"self": 1.9139988580718637e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.17483655499927409, |
|
"count": 1, |
|
"self": 0.002435280999634415, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.17240127399963967, |
|
"count": 1, |
|
"self": 0.17240127399963967 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |