|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.3993273079395294, |
|
"min": 0.39879706501960754, |
|
"max": 1.4075472354888916, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 11903.1484375, |
|
"min": 11903.1484375, |
|
"max": 42699.3515625, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989901.0, |
|
"min": 29952.0, |
|
"max": 989901.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989901.0, |
|
"min": 29952.0, |
|
"max": 989901.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.3363831043243408, |
|
"min": -0.09305348992347717, |
|
"max": 0.4777947962284088, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 86.7868423461914, |
|
"min": -22.425891876220703, |
|
"max": 127.57121276855469, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.014396990649402142, |
|
"min": 0.005339625291526318, |
|
"max": 0.49716049432754517, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 3.714423656463623, |
|
"min": 1.3883025646209717, |
|
"max": 117.82703399658203, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.0688180060410458, |
|
"min": 0.06573826706347366, |
|
"max": 0.07368404493168344, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.0322700906156872, |
|
"min": 0.5056364515362421, |
|
"max": 1.072765252533524, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.011931448857487538, |
|
"min": 0.0006445780829825771, |
|
"max": 0.013996165146231417, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.17897173286231308, |
|
"min": 0.008379515078773502, |
|
"max": 0.19594631204723983, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.493837502086667e-06, |
|
"min": 7.493837502086667e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00011240756253130001, |
|
"min": 0.00011240756253130001, |
|
"max": 0.0035077622307459998, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10249791333333334, |
|
"min": 0.10249791333333334, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5374687000000002, |
|
"min": 1.3886848, |
|
"max": 2.5692540000000004, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.000259541542, |
|
"min": 0.000259541542, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.00389312313, |
|
"min": 0.00389312313, |
|
"max": 0.11694847459999999, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.012906261719763279, |
|
"min": 0.012906261719763279, |
|
"max": 0.5758739113807678, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.19359391927719116, |
|
"min": 0.18395093083381653, |
|
"max": 4.0311174392700195, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 460.58730158730157, |
|
"min": 420.36486486486484, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29017.0, |
|
"min": 15984.0, |
|
"max": 33670.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.31714599591399, |
|
"min": -1.0000000521540642, |
|
"max": 1.3958506810833031, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 82.98019774258137, |
|
"min": -28.567001722753048, |
|
"max": 99.10539835691452, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.31714599591399, |
|
"min": -1.0000000521540642, |
|
"max": 1.3958506810833031, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 82.98019774258137, |
|
"min": -28.567001722753048, |
|
"max": 99.10539835691452, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.06161386090042513, |
|
"min": 0.059896824407799504, |
|
"max": 12.390749288722873, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.881673236726783, |
|
"min": 3.8789865077123977, |
|
"max": 198.25198861956596, |
|
"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": "1688728587", |
|
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --force --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --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": "1688730758" |
|
}, |
|
"total": 2171.402240441, |
|
"count": 1, |
|
"self": 0.48704856499989546, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.041545475000020815, |
|
"count": 1, |
|
"self": 0.041545475000020815 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2170.873646401, |
|
"count": 1, |
|
"self": 1.2780909149860236, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 5.592129784000008, |
|
"count": 1, |
|
"self": 5.592129784000008 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2163.907685954014, |
|
"count": 63590, |
|
"self": 1.3569457000276088, |
|
"children": { |
|
"env_step": { |
|
"total": 1495.9557870339877, |
|
"count": 63590, |
|
"self": 1386.9681721089134, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 108.18369374701979, |
|
"count": 63590, |
|
"self": 4.610368527051378, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 103.57332521996841, |
|
"count": 62565, |
|
"self": 103.57332521996841 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.803921178054452, |
|
"count": 63590, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2166.0152255850217, |
|
"count": 63590, |
|
"is_parallel": true, |
|
"self": 892.2071577069939, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.004153011999960654, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0028105449998747645, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013424670000858896, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013424670000858896 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.09517792700012251, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006003729999974894, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004781430000093678, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004781430000093678 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.09219945100016957, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.09219945100016957 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.001899959999946077, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00040118899983099254, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0014987710001150845, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0014987710001150845 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1273.8080678780277, |
|
"count": 63589, |
|
"is_parallel": true, |
|
"self": 34.387914918969955, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 22.50720429000262, |
|
"count": 63589, |
|
"is_parallel": true, |
|
"self": 22.50720429000262 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1114.078658397018, |
|
"count": 63589, |
|
"is_parallel": true, |
|
"self": 1114.078658397018 |
|
}, |
|
"steps_from_proto": { |
|
"total": 102.83429027203715, |
|
"count": 63589, |
|
"is_parallel": true, |
|
"self": 19.662673347028885, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 83.17161692500827, |
|
"count": 508712, |
|
"is_parallel": true, |
|
"self": 83.17161692500827 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 666.5949532199988, |
|
"count": 63590, |
|
"self": 2.5212363999812624, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 111.45025194301911, |
|
"count": 63590, |
|
"self": 111.2453897050193, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.20486223799980507, |
|
"count": 2, |
|
"self": 0.20486223799980507 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 552.6234648769985, |
|
"count": 450, |
|
"self": 357.71526976902055, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 194.90819510797792, |
|
"count": 22800, |
|
"self": 194.90819510797792 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.739997040014714e-07, |
|
"count": 1, |
|
"self": 9.739997040014714e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.0957387739999831, |
|
"count": 1, |
|
"self": 0.0014004289996591979, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.0943383450003239, |
|
"count": 1, |
|
"self": 0.0943383450003239 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |