|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.02970881387591362, |
|
"min": 0.005502134095877409, |
|
"max": 1.458825945854187, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 883.658935546875, |
|
"min": 164.7999267578125, |
|
"max": 44254.9453125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989895.0, |
|
"min": 29976.0, |
|
"max": 989895.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989895.0, |
|
"min": 29976.0, |
|
"max": 989895.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.10165281593799591, |
|
"min": -0.11501456052064896, |
|
"max": -0.05839862674474716, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -24.193370819091797, |
|
"min": -27.60349464416504, |
|
"max": -14.132467269897461, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 1.7020528316497803, |
|
"min": 0.170526921749115, |
|
"max": 1.8837361335754395, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 405.08856201171875, |
|
"min": 40.58540725708008, |
|
"max": 452.0966796875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06676959379212441, |
|
"min": 0.06504628872538963, |
|
"max": 0.07305271990977844, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.8680047192976172, |
|
"min": 0.511369039368449, |
|
"max": 0.9294779065483632, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.010006159010320688, |
|
"min": 0.007283555994805915, |
|
"max": 0.013096564808702471, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.13008006713416895, |
|
"min": 0.053525364753395796, |
|
"max": 0.15715877770442965, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.401997532700006e-06, |
|
"min": 7.401997532700006e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 9.622596792510008e-05, |
|
"min": 9.622596792510008e-05, |
|
"max": 0.0034935184354938993, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10246730000000003, |
|
"min": 0.10246730000000003, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.3320749000000003, |
|
"min": 1.2658052000000002, |
|
"max": 2.4645061, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00025648327000000017, |
|
"min": 0.00025648327000000017, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003334282510000002, |
|
"min": 0.003334282510000002, |
|
"max": 0.11646415938999999, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 1.722501277923584, |
|
"min": 0.4974973201751709, |
|
"max": 1.8506916761398315, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 22.39251708984375, |
|
"min": 3.4824812412261963, |
|
"max": 23.83445930480957, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 999.0, |
|
"min": 963.2647058823529, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 20979.0, |
|
"min": 16775.0, |
|
"max": 32751.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": -0.9997143358701751, |
|
"min": -0.9998533844947814, |
|
"max": -0.7876647563979906, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": -20.994001053273678, |
|
"min": -31.994001626968384, |
|
"max": -14.791000872850418, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": -0.9997143358701751, |
|
"min": -0.9998533844947814, |
|
"max": -0.7876647563979906, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": -20.994001053273678, |
|
"min": -31.994001626968384, |
|
"max": -14.791000872850418, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 16.717697711489606, |
|
"min": 7.600432110621648, |
|
"max": 18.57363071364741, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 351.07165194128174, |
|
"min": 148.92243483662605, |
|
"max": 592.772442755755, |
|
"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": "1675945792", |
|
"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": "1675948146" |
|
}, |
|
"total": 2354.0459201940002, |
|
"count": 1, |
|
"self": 0.6439772789999552, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.12278756199998497, |
|
"count": 1, |
|
"self": 0.12278756199998497 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2353.279155353, |
|
"count": 1, |
|
"self": 2.081998420052514, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 7.86767890200008, |
|
"count": 1, |
|
"self": 7.86767890200008 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2343.2377247389477, |
|
"count": 62799, |
|
"self": 2.22269723001682, |
|
"children": { |
|
"env_step": { |
|
"total": 1503.2693276010125, |
|
"count": 62799, |
|
"self": 1340.8418320559715, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 161.13611666202473, |
|
"count": 62799, |
|
"self": 6.049010860062481, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 155.08710580196225, |
|
"count": 62560, |
|
"self": 51.99187968593924, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 103.09522611602301, |
|
"count": 62560, |
|
"self": 103.09522611602301 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 1.2913788830162503, |
|
"count": 62799, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2347.135065440056, |
|
"count": 62799, |
|
"is_parallel": true, |
|
"self": 1158.8975543620913, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0020950560001438134, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000771768000049633, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013232880000941805, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013232880000941805 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05489538200004063, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006656040000052599, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0006200699999681092, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006200699999681092 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.05146886800002903, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.05146886800002903 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0021408400000382244, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005915770002502541, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0015492629997879703, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0015492629997879703 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1188.2375110779649, |
|
"count": 62798, |
|
"is_parallel": true, |
|
"self": 38.27477738599396, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 28.47892558299668, |
|
"count": 62798, |
|
"is_parallel": true, |
|
"self": 28.47892558299668 |
|
}, |
|
"communicator.exchange": { |
|
"total": 994.3962634630111, |
|
"count": 62798, |
|
"is_parallel": true, |
|
"self": 994.3962634630111 |
|
}, |
|
"steps_from_proto": { |
|
"total": 127.08754464596313, |
|
"count": 62798, |
|
"is_parallel": true, |
|
"self": 29.499671642061685, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 97.58787300390145, |
|
"count": 502384, |
|
"is_parallel": true, |
|
"self": 97.58787300390145 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 837.7456999079184, |
|
"count": 62799, |
|
"self": 3.1884801059495658, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 191.33308089297088, |
|
"count": 62799, |
|
"self": 191.12629961497123, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.20678127799965296, |
|
"count": 2, |
|
"self": 0.20678127799965296 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 643.2241389089979, |
|
"count": 411, |
|
"self": 239.42813052697215, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 403.7960083820258, |
|
"count": 22896, |
|
"self": 403.7960083820258 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.799997885944322e-07, |
|
"count": 1, |
|
"self": 8.799997885944322e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09175241200000528, |
|
"count": 1, |
|
"self": 0.0015243359998748929, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09022807600013039, |
|
"count": 1, |
|
"self": 0.09022807600013039 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |