|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.8404826521873474, |
|
"min": 0.8404826521873474, |
|
"max": 1.4598430395126343, |
|
"count": 10 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 25106.8984375, |
|
"min": 25106.8984375, |
|
"max": 44285.796875, |
|
"count": 10 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 299952.0, |
|
"min": 29952.0, |
|
"max": 299952.0, |
|
"count": 10 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 299952.0, |
|
"min": 29952.0, |
|
"max": 299952.0, |
|
"count": 10 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.03310125693678856, |
|
"min": -0.07654073089361191, |
|
"max": 0.1605910360813141, |
|
"count": 10 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -8.010503768920898, |
|
"min": -18.44631576538086, |
|
"max": 38.06007385253906, |
|
"count": 10 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.019918009638786316, |
|
"min": 0.019918009638786316, |
|
"max": 0.28890857100486755, |
|
"count": 10 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 4.8201584815979, |
|
"min": 4.8201584815979, |
|
"max": 68.47132873535156, |
|
"count": 10 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06773245448382904, |
|
"min": 0.06645605675805881, |
|
"max": 0.07163800704222076, |
|
"count": 10 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9482543627736065, |
|
"min": 0.49019168771990046, |
|
"max": 0.9815040180547381, |
|
"count": 10 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.0028364419568095494, |
|
"min": 0.0004969434000239663, |
|
"max": 0.006827787384967173, |
|
"count": 10 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.03971018739533369, |
|
"min": 0.005963320800287596, |
|
"max": 0.06437933459762338, |
|
"count": 10 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 1.5029594990166666e-05, |
|
"min": 1.5029594990166666e-05, |
|
"max": 0.0002838354339596191, |
|
"count": 10 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00021041432986233333, |
|
"min": 0.00021041432986233333, |
|
"max": 0.0023461314179563336, |
|
"count": 10 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10500983333333334, |
|
"min": 0.10500983333333334, |
|
"max": 0.19461180952380958, |
|
"count": 10 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4701376666666668, |
|
"min": 1.362282666666667, |
|
"max": 2.03139, |
|
"count": 10 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00051048235, |
|
"min": 0.00051048235, |
|
"max": 0.00946171977142857, |
|
"count": 10 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.007146752900000001, |
|
"min": 0.007146752900000001, |
|
"max": 0.07824616229999999, |
|
"count": 10 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.02987137995660305, |
|
"min": 0.02987137995660305, |
|
"max": 0.363151490688324, |
|
"count": 10 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.4181993305683136, |
|
"min": 0.4181993305683136, |
|
"max": 2.542060375213623, |
|
"count": 10 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 953.8125, |
|
"min": 882.1034482758621, |
|
"max": 999.0, |
|
"count": 10 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30522.0, |
|
"min": 15984.0, |
|
"max": 32618.0, |
|
"count": 10 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": -0.5657613385588892, |
|
"min": -1.0000000521540642, |
|
"max": -0.26180694740394067, |
|
"count": 10 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": -17.538601495325565, |
|
"min": -30.65000168979168, |
|
"max": -7.592401474714279, |
|
"count": 10 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": -0.5657613385588892, |
|
"min": -1.0000000521540642, |
|
"max": -0.26180694740394067, |
|
"count": 10 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": -17.538601495325565, |
|
"min": -30.65000168979168, |
|
"max": -7.592401474714279, |
|
"count": 10 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.30023005015156684, |
|
"min": 0.30023005015156684, |
|
"max": 7.17590135615319, |
|
"count": 10 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 9.307131554698572, |
|
"min": 8.91508346516639, |
|
"max": 114.81442169845104, |
|
"count": 10 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 10 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 10 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1676561680", |
|
"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": "1.21.6", |
|
"end_time_seconds": "1676562704" |
|
}, |
|
"total": 1024.5575820230001, |
|
"count": 1, |
|
"self": 0.6995505899999443, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.1480947869999909, |
|
"count": 1, |
|
"self": 0.1480947869999909 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1023.7099366460002, |
|
"count": 1, |
|
"self": 0.7865703300121822, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 5.383240442999977, |
|
"count": 1, |
|
"self": 5.383240442999977 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1017.4169878609878, |
|
"count": 18897, |
|
"self": 0.8082753710023098, |
|
"children": { |
|
"env_step": { |
|
"total": 619.0710352310152, |
|
"count": 18897, |
|
"self": 571.8386058710821, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 46.70313683396262, |
|
"count": 18897, |
|
"self": 2.2971994609656576, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 44.40593737299696, |
|
"count": 18794, |
|
"self": 9.849545270017188, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 34.55639210297977, |
|
"count": 18794, |
|
"self": 34.55639210297977 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.5292925259705044, |
|
"count": 18897, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1021.5677363160107, |
|
"count": 18897, |
|
"is_parallel": true, |
|
"self": 507.5499073669962, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.003455330999713624, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0015149869996093912, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0019403440001042327, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0019403440001042327 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.07122465100019326, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006838459999016777, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005478600000969891, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005478600000969891 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.06766062799988504, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.06766062799988504 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0023323170003095584, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006167400001686474, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001715577000140911, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001715577000140911 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 514.0178289490145, |
|
"count": 18896, |
|
"is_parallel": true, |
|
"self": 14.077046086012615, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 8.6963265929935, |
|
"count": 18896, |
|
"is_parallel": true, |
|
"self": 8.6963265929935 |
|
}, |
|
"communicator.exchange": { |
|
"total": 449.5596541469986, |
|
"count": 18896, |
|
"is_parallel": true, |
|
"self": 449.5596541469986 |
|
}, |
|
"steps_from_proto": { |
|
"total": 41.68480212300983, |
|
"count": 18896, |
|
"is_parallel": true, |
|
"self": 10.560656833954454, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 31.124145289055377, |
|
"count": 151168, |
|
"is_parallel": true, |
|
"self": 31.124145289055377 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 397.53767725897023, |
|
"count": 18897, |
|
"self": 1.3109092859881457, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 74.87929048998103, |
|
"count": 18897, |
|
"self": 74.87929048998103 |
|
}, |
|
"_update_policy": { |
|
"total": 321.34747748300106, |
|
"count": 118, |
|
"self": 87.390586292021, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 233.95689119098006, |
|
"count": 6882, |
|
"self": 233.95689119098006 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.261999841517536e-06, |
|
"count": 1, |
|
"self": 1.261999841517536e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.12313675000041258, |
|
"count": 1, |
|
"self": 0.002378926000346837, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.12075782400006574, |
|
"count": 1, |
|
"self": 0.12075782400006574 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |