|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.1847091168165207, |
|
"min": 0.16502724587917328, |
|
"max": 1.4427882432937622, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 5520.5859375, |
|
"min": 4919.13232421875, |
|
"max": 43768.42578125, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 2999996.0, |
|
"min": 29952.0, |
|
"max": 2999996.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 2999996.0, |
|
"min": 29952.0, |
|
"max": 2999996.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.7377480864524841, |
|
"min": -0.10434343665838242, |
|
"max": 0.8859363794326782, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 219.11117553710938, |
|
"min": -25.14676856994629, |
|
"max": 273.75433349609375, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.01645086333155632, |
|
"min": -0.02501700073480606, |
|
"max": 0.2722559869289398, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 4.885906219482422, |
|
"min": -6.929709434509277, |
|
"max": 65.34143829345703, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.0679712892507225, |
|
"min": 0.06538511255205902, |
|
"max": 0.0729599837731156, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9515980495101151, |
|
"min": 0.46804286222841357, |
|
"max": 1.094399756596734, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.01645695645545077, |
|
"min": 0.0005489715020402621, |
|
"max": 0.01645695645545077, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.23039739037631077, |
|
"min": 0.00768560102856367, |
|
"max": 0.24440671205606865, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 1.427649524149997e-06, |
|
"min": 1.427649524149997e-06, |
|
"max": 0.00029838354339596195, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 1.9987093338099958e-05, |
|
"min": 1.9987093338099958e-05, |
|
"max": 0.003969591576802833, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10047585000000002, |
|
"min": 0.10047585000000002, |
|
"max": 0.19946118095238097, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4066619000000002, |
|
"min": 1.3962282666666668, |
|
"max": 2.723197166666667, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 5.753741499999991e-05, |
|
"min": 5.753741499999991e-05, |
|
"max": 0.009946171977142856, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0008055238099999988, |
|
"min": 0.0008055238099999988, |
|
"max": 0.13232739695, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.006958275102078915, |
|
"min": 0.0066532474011182785, |
|
"max": 0.40524861216545105, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.09741584956645966, |
|
"min": 0.09318860620260239, |
|
"max": 2.836740255355835, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 217.14084507042253, |
|
"min": 211.6853146853147, |
|
"max": 999.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30834.0, |
|
"min": 15984.0, |
|
"max": 32367.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.7696853016952534, |
|
"min": -1.0000000521540642, |
|
"max": 1.7779699069888968, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 253.06499814242125, |
|
"min": -29.978001676499844, |
|
"max": 253.06499814242125, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.7696853016952534, |
|
"min": -1.0000000521540642, |
|
"max": 1.7779699069888968, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 253.06499814242125, |
|
"min": -29.978001676499844, |
|
"max": 253.06499814242125, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.015636616752408055, |
|
"min": 0.015636616752408055, |
|
"max": 8.125284284353256, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.2360361955943517, |
|
"min": 1.9766774149320554, |
|
"max": 130.0045485496521, |
|
"count": 100 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 100 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1678020955", |
|
"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": "1678028114" |
|
}, |
|
"total": 7159.191377724001, |
|
"count": 1, |
|
"self": 0.4899057700013145, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.128781637999964, |
|
"count": 1, |
|
"self": 0.128781637999964 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 7158.572690315999, |
|
"count": 1, |
|
"self": 4.132209827668703, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.555238698000039, |
|
"count": 1, |
|
"self": 6.555238698000039 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 7147.798560349331, |
|
"count": 194649, |
|
"self": 4.257957457156408, |
|
"children": { |
|
"env_step": { |
|
"total": 4926.220886086981, |
|
"count": 194649, |
|
"self": 4594.862116669014, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 328.89110174095686, |
|
"count": 194649, |
|
"self": 13.881333534898204, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 315.00976820605865, |
|
"count": 187556, |
|
"self": 107.29369561769363, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 207.71607258836502, |
|
"count": 187556, |
|
"self": 207.71607258836502 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 2.4676676770109225, |
|
"count": 194649, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 7143.591759959156, |
|
"count": 194649, |
|
"is_parallel": true, |
|
"self": 2895.7591608660696, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0018131659999198746, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006322870001440606, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001180878999775814, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001180878999775814 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.08313087800001995, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007126410000637406, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005046860001129971, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005046860001129971 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.08032876299989766, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.08032876299989766 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0015847879999455472, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003902789997027867, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011945090002427605, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011945090002427605 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 4247.832599093086, |
|
"count": 194648, |
|
"is_parallel": true, |
|
"self": 93.84757718136825, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 68.4469871500387, |
|
"count": 194648, |
|
"is_parallel": true, |
|
"self": 68.4469871500387 |
|
}, |
|
"communicator.exchange": { |
|
"total": 3809.4012219978836, |
|
"count": 194648, |
|
"is_parallel": true, |
|
"self": 3809.4012219978836 |
|
}, |
|
"steps_from_proto": { |
|
"total": 276.1368127637959, |
|
"count": 194648, |
|
"is_parallel": true, |
|
"self": 65.94802634180132, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 210.18878642199456, |
|
"count": 1557184, |
|
"is_parallel": true, |
|
"self": 210.18878642199456 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 2217.319716805193, |
|
"count": 194649, |
|
"self": 8.13676059719046, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 495.04897086901474, |
|
"count": 194649, |
|
"self": 494.4745665220148, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.5744043469999269, |
|
"count": 6, |
|
"self": 0.5744043469999269 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1714.1339853389877, |
|
"count": 1399, |
|
"self": 671.0731828579565, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 1043.0608024810313, |
|
"count": 68421, |
|
"self": 1043.0608024810313 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.229999366449192e-07, |
|
"count": 1, |
|
"self": 8.229999366449192e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08668061800017313, |
|
"count": 1, |
|
"self": 0.0014751210001122672, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.08520549700006086, |
|
"count": 1, |
|
"self": 0.08520549700006086 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |