|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.31833627820014954, |
|
"min": 0.3061375617980957, |
|
"max": 1.4977558851242065, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 9621.3955078125, |
|
"min": 9159.6357421875, |
|
"max": 45435.921875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989880.0, |
|
"min": 29980.0, |
|
"max": 989880.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989880.0, |
|
"min": 29980.0, |
|
"max": 989880.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.5198135375976562, |
|
"min": -0.09395303577184677, |
|
"max": 0.5358319878578186, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 145.02796936035156, |
|
"min": -22.548728942871094, |
|
"max": 147.35379028320312, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -1.5147697922657244e-05, |
|
"min": -0.005624157376587391, |
|
"max": 0.16539013385772705, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -0.004226207733154297, |
|
"min": -1.541019082069397, |
|
"max": 40.0244140625, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06817232392809362, |
|
"min": 0.06516737303682225, |
|
"max": 0.0719690171688507, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9544125349933108, |
|
"min": 0.5651824746425109, |
|
"max": 1.0658915565387967, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.017320355433378502, |
|
"min": 0.00012263453249437993, |
|
"max": 0.017320355433378502, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.24248497606729905, |
|
"min": 0.001594248922426939, |
|
"max": 0.24248497606729905, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.240254729471427e-06, |
|
"min": 7.240254729471427e-06, |
|
"max": 0.00029492325169225004, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010136356621259997, |
|
"min": 0.00010136356621259997, |
|
"max": 0.0033316608894463995, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10241338571428571, |
|
"min": 0.10241338571428571, |
|
"max": 0.19830775, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4337874, |
|
"min": 1.4337874, |
|
"max": 2.4011627, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00025109723285714284, |
|
"min": 0.00025109723285714284, |
|
"max": 0.009830944224999999, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0035153612599999997, |
|
"min": 0.0035153612599999997, |
|
"max": 0.11106430464000001, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.011059997603297234, |
|
"min": 0.01060000155121088, |
|
"max": 0.3147541880607605, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.15483996272087097, |
|
"min": 0.1498698592185974, |
|
"max": 2.518033504486084, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 324.0, |
|
"min": 324.0, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29808.0, |
|
"min": 16650.0, |
|
"max": 33050.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.5890217195062533, |
|
"min": -0.9999267183244228, |
|
"max": 1.5890217195062533, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 146.1899981945753, |
|
"min": -31.997201651334763, |
|
"max": 146.1899981945753, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.5890217195062533, |
|
"min": -0.9999267183244228, |
|
"max": 1.5890217195062533, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 146.1899981945753, |
|
"min": -31.997201651334763, |
|
"max": 146.1899981945753, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.03721140466476082, |
|
"min": 0.03721140466476082, |
|
"max": 5.757969638539685, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.4234492291579954, |
|
"min": 3.320987312516081, |
|
"max": 103.64345349371433, |
|
"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": "1677249624", |
|
"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=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": "1677251844" |
|
}, |
|
"total": 2220.181945151, |
|
"count": 1, |
|
"self": 0.5261430100003963, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.10957014399991749, |
|
"count": 1, |
|
"self": 0.10957014399991749 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2219.5462319969997, |
|
"count": 1, |
|
"self": 1.348981578036728, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 7.165586283000039, |
|
"count": 1, |
|
"self": 7.165586283000039 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2210.9421604819627, |
|
"count": 63753, |
|
"self": 1.367671524988964, |
|
"children": { |
|
"env_step": { |
|
"total": 1466.8089763539915, |
|
"count": 63753, |
|
"self": 1355.196354736008, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 110.77726097401933, |
|
"count": 63753, |
|
"self": 4.655739099085849, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 106.12152187493348, |
|
"count": 62554, |
|
"self": 35.81815920296822, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 70.30336267196526, |
|
"count": 62554, |
|
"self": 70.30336267196526 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.8353606439641226, |
|
"count": 63753, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2214.6281508120323, |
|
"count": 63753, |
|
"is_parallel": true, |
|
"self": 973.6714881180421, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.002023282999971343, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006798690003506636, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013434139996206795, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013434139996206795 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04534347300000263, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005400699999427161, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00043938499993601, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00043938499993601 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.042768442000124196, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.042768442000124196 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.00159557599999971, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004113959998903738, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001184180000109336, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001184180000109336 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1240.9566626939902, |
|
"count": 63752, |
|
"is_parallel": true, |
|
"self": 31.02994701222383, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 22.491031984940946, |
|
"count": 63752, |
|
"is_parallel": true, |
|
"self": 22.491031984940946 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1086.8780218049415, |
|
"count": 63752, |
|
"is_parallel": true, |
|
"self": 1086.8780218049415 |
|
}, |
|
"steps_from_proto": { |
|
"total": 100.55766189188398, |
|
"count": 63752, |
|
"is_parallel": true, |
|
"self": 22.179717499858725, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 78.37794439202526, |
|
"count": 510016, |
|
"is_parallel": true, |
|
"self": 78.37794439202526 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 742.7655126029822, |
|
"count": 63753, |
|
"self": 2.4864543160072117, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 160.9474290189737, |
|
"count": 63753, |
|
"self": 160.76419550997343, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.18323350900027435, |
|
"count": 2, |
|
"self": 0.18323350900027435 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 579.3316292680013, |
|
"count": 450, |
|
"self": 227.7218803159924, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 351.6097489520089, |
|
"count": 22764, |
|
"self": 351.6097489520089 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0220001058769412e-06, |
|
"count": 1, |
|
"self": 1.0220001058769412e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08950263199994879, |
|
"count": 1, |
|
"self": 0.00174601500020799, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.0877566169997408, |
|
"count": 1, |
|
"self": 0.0877566169997408 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |