|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.3908621668815613, |
|
"min": 0.38359513878822327, |
|
"max": 1.4590368270874023, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 11807.1640625, |
|
"min": 11415.791015625, |
|
"max": 44261.33984375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989881.0, |
|
"min": 29897.0, |
|
"max": 989881.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989881.0, |
|
"min": 29897.0, |
|
"max": 989881.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.6767734289169312, |
|
"min": -0.10698991268873215, |
|
"max": 0.7063584923744202, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 194.23397827148438, |
|
"min": -25.356609344482422, |
|
"max": 206.96304321289062, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.02619103156030178, |
|
"min": -0.011437329463660717, |
|
"max": 0.299892395734787, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 7.516826152801514, |
|
"min": -3.2253270149230957, |
|
"max": 72.2740707397461, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06528362203001356, |
|
"min": 0.06506264701602048, |
|
"max": 0.07333710537585872, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9139707084201898, |
|
"min": 0.4930213629768227, |
|
"max": 1.0716038072132505, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.016887424933277845, |
|
"min": 0.0004764606642033617, |
|
"max": 0.016887424933277845, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.23642394906588984, |
|
"min": 0.005241067306236979, |
|
"max": 0.23642394906588984, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.4584403710285675e-06, |
|
"min": 7.4584403710285675e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010441816519439995, |
|
"min": 0.00010441816519439995, |
|
"max": 0.0035036387321204995, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.1024861142857143, |
|
"min": 0.1024861142857143, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4348056000000002, |
|
"min": 1.3886848, |
|
"max": 2.5678794999999996, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.000258362817142857, |
|
"min": 0.000258362817142857, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0036170794399999983, |
|
"min": 0.0036170794399999983, |
|
"max": 0.11681116205000001, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.01021169126033783, |
|
"min": 0.01021169126033783, |
|
"max": 0.557073175907135, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.14296367764472961, |
|
"min": 0.14296367764472961, |
|
"max": 3.8995120525360107, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 292.4271844660194, |
|
"min": 261.88495575221236, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30120.0, |
|
"min": 16824.0, |
|
"max": 32131.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.707403828891424, |
|
"min": -0.9999750521965325, |
|
"max": 1.7204070628612442, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 177.5699982047081, |
|
"min": -31.99920167028904, |
|
"max": 194.4059981033206, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.707403828891424, |
|
"min": -0.9999750521965325, |
|
"max": 1.7204070628612442, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 177.5699982047081, |
|
"min": -31.99920167028904, |
|
"max": 194.4059981033206, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.030941790644227203, |
|
"min": 0.030941790644227203, |
|
"max": 11.355583505595432, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.2179462269996293, |
|
"min": 3.117691306397319, |
|
"max": 193.04491959512234, |
|
"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": "1678214761", |
|
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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=new 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": "1.22.4", |
|
"end_time_seconds": "1678217253" |
|
}, |
|
"total": 2492.4301391530003, |
|
"count": 1, |
|
"self": 0.5990411000002496, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.10817222899999024, |
|
"count": 1, |
|
"self": 0.10817222899999024 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2491.722925824, |
|
"count": 1, |
|
"self": 1.518234807009776, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 9.287128419999988, |
|
"count": 1, |
|
"self": 9.287128419999988 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2480.8281484669897, |
|
"count": 64120, |
|
"self": 1.6936405079850374, |
|
"children": { |
|
"env_step": { |
|
"total": 1721.6618343609878, |
|
"count": 64120, |
|
"self": 1598.5353372779796, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 122.1850049990095, |
|
"count": 64120, |
|
"self": 5.092636900019045, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 117.09236809899045, |
|
"count": 62578, |
|
"self": 39.63625047299911, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 77.45611762599134, |
|
"count": 62578, |
|
"self": 77.45611762599134 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.9414920839988099, |
|
"count": 64120, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2485.651734907009, |
|
"count": 64120, |
|
"is_parallel": true, |
|
"self": 1015.9665215099951, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0069005119999587805, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.003244921999964845, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0036555899999939356, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0036555899999939356 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04973598999998785, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005387390000350933, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00048167799997145266, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00048167799997145266 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04692355999998199, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04692355999998199 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.001792012999999315, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00042532500003744644, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013666879999618686, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013666879999618686 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1469.685213397014, |
|
"count": 64119, |
|
"is_parallel": true, |
|
"self": 33.606401556960236, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 25.789806417015598, |
|
"count": 64119, |
|
"is_parallel": true, |
|
"self": 25.789806417015598 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1308.7842966580106, |
|
"count": 64119, |
|
"is_parallel": true, |
|
"self": 1308.7842966580106 |
|
}, |
|
"steps_from_proto": { |
|
"total": 101.50470876502749, |
|
"count": 64119, |
|
"is_parallel": true, |
|
"self": 24.914584607213612, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 76.59012415781388, |
|
"count": 512952, |
|
"is_parallel": true, |
|
"self": 76.59012415781388 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 757.4726735980167, |
|
"count": 64120, |
|
"self": 2.880847835018244, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 175.61445800100387, |
|
"count": 64120, |
|
"self": 175.41531721300385, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.19914078800002244, |
|
"count": 2, |
|
"self": 0.19914078800002244 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 578.9773677619946, |
|
"count": 456, |
|
"self": 224.34490202600097, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 354.63246573599366, |
|
"count": 22761, |
|
"self": 354.63246573599366 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0200001270277426e-06, |
|
"count": 1, |
|
"self": 1.0200001270277426e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08941311000035057, |
|
"count": 1, |
|
"self": 0.001447168000140664, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.0879659420002099, |
|
"count": 1, |
|
"self": 0.0879659420002099 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |