|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.49036848545074463, |
|
"min": 0.486410915851593, |
|
"max": 1.4026033878326416, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 14687.5166015625, |
|
"min": 14561.197265625, |
|
"max": 42549.375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989988.0, |
|
"min": 29952.0, |
|
"max": 989988.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989988.0, |
|
"min": 29952.0, |
|
"max": 989988.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.4223002791404724, |
|
"min": -0.11120632290840149, |
|
"max": 0.4663859009742737, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 111.90957641601562, |
|
"min": -26.689517974853516, |
|
"max": 125.9241943359375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.029169755056500435, |
|
"min": -0.04761064052581787, |
|
"max": 0.5099064707756042, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -7.729985237121582, |
|
"min": -12.99770450592041, |
|
"max": 120.84783935546875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06943094012703369, |
|
"min": 0.06517950096029035, |
|
"max": 0.07293299871511323, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.0414641019055053, |
|
"min": 0.46201161289455145, |
|
"max": 1.0462445375240206, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.015245787126108778, |
|
"min": 0.0003966667606918153, |
|
"max": 0.015245787126108778, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.22868680689163168, |
|
"min": 0.005553334649685414, |
|
"max": 0.22868680689163168, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.53697748770667e-06, |
|
"min": 7.53697748770667e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00011305466231560005, |
|
"min": 0.00011305466231560005, |
|
"max": 0.0035073248308918, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10251229333333332, |
|
"min": 0.10251229333333332, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5376843999999998, |
|
"min": 1.3691136000000002, |
|
"max": 2.5691081999999996, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002609781040000001, |
|
"min": 0.0002609781040000001, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003914671560000002, |
|
"min": 0.003914671560000002, |
|
"max": 0.11693390918000002, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.011221312917768955, |
|
"min": 0.011221312917768955, |
|
"max": 0.4665204584598541, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.1683196872472763, |
|
"min": 0.15938179194927216, |
|
"max": 3.2656431198120117, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 426.4782608695652, |
|
"min": 399.64473684210526, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29427.0, |
|
"min": 15984.0, |
|
"max": 33142.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.5155304109920626, |
|
"min": -1.0000000521540642, |
|
"max": 1.5155304109920626, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 104.57159835845232, |
|
"min": -32.000001668930054, |
|
"max": 108.96599830687046, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.5155304109920626, |
|
"min": -1.0000000521540642, |
|
"max": 1.5155304109920626, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 104.57159835845232, |
|
"min": -32.000001668930054, |
|
"max": 108.96599830687046, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.04952129925009828, |
|
"min": 0.048265587657612435, |
|
"max": 9.488236006349325, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.4169696482567815, |
|
"min": 3.4169696482567815, |
|
"max": 151.8117761015892, |
|
"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": "1660735750", |
|
"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": "1660737898" |
|
}, |
|
"total": 2148.161661367, |
|
"count": 1, |
|
"self": 0.47758982400000605, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0425828500000307, |
|
"count": 1, |
|
"self": 0.0425828500000307 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2147.6414886929997, |
|
"count": 1, |
|
"self": 1.631994849989951, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 10.765427003000013, |
|
"count": 1, |
|
"self": 10.765427003000013 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2135.142926334009, |
|
"count": 63519, |
|
"self": 1.7786469871093686, |
|
"children": { |
|
"env_step": { |
|
"total": 1399.9591235809191, |
|
"count": 63519, |
|
"self": 1279.1165842338612, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 119.97922112404171, |
|
"count": 63519, |
|
"self": 5.118945442051995, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 114.86027568198972, |
|
"count": 62552, |
|
"self": 38.07204256300179, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 76.78823311898793, |
|
"count": 62552, |
|
"self": 76.78823311898793 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.863318223016222, |
|
"count": 63519, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2143.273093531988, |
|
"count": 63519, |
|
"is_parallel": true, |
|
"self": 979.0778995569606, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.005019514999958119, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0037374869997393034, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012820280002188156, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012820280002188156 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05164784700002656, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005350100001351166, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004698679999819433, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004698679999819433 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04866606299992782, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04866606299992782 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.001976905999981682, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004949650001435657, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0014819409998381161, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0014819409998381161 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1164.1951939750272, |
|
"count": 63518, |
|
"is_parallel": true, |
|
"self": 28.733637617027625, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 26.1037943350384, |
|
"count": 63518, |
|
"is_parallel": true, |
|
"self": 26.1037943350384 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1007.6158848889719, |
|
"count": 63518, |
|
"is_parallel": true, |
|
"self": 1007.6158848889719 |
|
}, |
|
"steps_from_proto": { |
|
"total": 101.7418771339893, |
|
"count": 63518, |
|
"is_parallel": true, |
|
"self": 25.751826282848356, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 75.99005085114095, |
|
"count": 508144, |
|
"is_parallel": true, |
|
"self": 75.99005085114095 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 733.4051557659807, |
|
"count": 63519, |
|
"self": 2.9503203970115237, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 175.42409041196902, |
|
"count": 63519, |
|
"self": 175.21349838296896, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.21059202900005403, |
|
"count": 2, |
|
"self": 0.21059202900005403 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 555.0307449570001, |
|
"count": 444, |
|
"self": 220.0455289239943, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 334.9852160330058, |
|
"count": 22785, |
|
"self": 334.9852160330058 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.2530003914434928e-06, |
|
"count": 1, |
|
"self": 1.2530003914434928e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.10113925299992843, |
|
"count": 1, |
|
"self": 0.0018365819996688515, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09930267100025958, |
|
"count": 1, |
|
"self": 0.09930267100025958 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |