|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.3689822256565094, |
|
"min": 0.36745572090148926, |
|
"max": 1.4303189516067505, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 11104.888671875, |
|
"min": 11058.947265625, |
|
"max": 43390.15625, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989915.0, |
|
"min": 29927.0, |
|
"max": 989915.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989915.0, |
|
"min": 29927.0, |
|
"max": 989915.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.7052223682403564, |
|
"min": -0.10139551758766174, |
|
"max": 0.7052223682403564, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 203.80926513671875, |
|
"min": -24.537715911865234, |
|
"max": 203.80926513671875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.007158319931477308, |
|
"min": -3.1499896522291237e-06, |
|
"max": 0.33016109466552734, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 2.0687544345855713, |
|
"min": -0.0008914470672607422, |
|
"max": 78.57833862304688, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06905312915370115, |
|
"min": 0.064839410388282, |
|
"max": 0.07306892432998643, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9667438081518162, |
|
"min": 0.6531862541772702, |
|
"max": 1.0824645417725312, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.015202213432385484, |
|
"min": 0.0010282811926775775, |
|
"max": 0.016710849940955848, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.21283098805339679, |
|
"min": 0.013367655504808507, |
|
"max": 0.2381094016275122, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.365054687871431e-06, |
|
"min": 7.365054687871431e-06, |
|
"max": 0.00029487820170726666, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010311076563020003, |
|
"min": 0.00010311076563020003, |
|
"max": 0.0036335290888237, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10245498571428575, |
|
"min": 0.10245498571428575, |
|
"max": 0.19829273333333333, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4343698000000005, |
|
"min": 1.4343698000000005, |
|
"max": 2.6111763000000003, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002552530728571429, |
|
"min": 0.0002552530728571429, |
|
"max": 0.00982944406, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0035735430200000006, |
|
"min": 0.0035735430200000006, |
|
"max": 0.12113651236999999, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.011849058791995049, |
|
"min": 0.011849058791995049, |
|
"max": 0.4638270139694214, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.16588681936264038, |
|
"min": 0.16588681936264038, |
|
"max": 4.174443244934082, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 278.06796116504853, |
|
"min": 278.06796116504853, |
|
"max": 987.34375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 28641.0, |
|
"min": 16214.0, |
|
"max": 33460.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.723586523762116, |
|
"min": -0.9257750504184514, |
|
"max": 1.723586523762116, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 179.25299847126007, |
|
"min": -30.291801631450653, |
|
"max": 179.25299847126007, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.723586523762116, |
|
"min": -0.9257750504184514, |
|
"max": 1.723586523762116, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 179.25299847126007, |
|
"min": -30.291801631450653, |
|
"max": 179.25299847126007, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.03379766845969593, |
|
"min": 0.03379766845969593, |
|
"max": 9.046550699016628, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.5149575198083767, |
|
"min": 3.5149575198083767, |
|
"max": 153.79136188328266, |
|
"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": "1708998204", |
|
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", |
|
"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": "1.1.0.dev0", |
|
"mlagents_envs_version": "1.1.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "2.2.1+cu121", |
|
"numpy_version": "1.23.5", |
|
"end_time_seconds": "1709000536" |
|
}, |
|
"total": 2331.2794666769996, |
|
"count": 1, |
|
"self": 0.7347737709992543, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.048952826999993704, |
|
"count": 1, |
|
"self": 0.048952826999993704 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2330.4957400790004, |
|
"count": 1, |
|
"self": 1.5180219300982571, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 2.4843124819999503, |
|
"count": 1, |
|
"self": 2.4843124819999503 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2326.359443516902, |
|
"count": 64132, |
|
"self": 1.580674755932705, |
|
"children": { |
|
"env_step": { |
|
"total": 1689.272531674063, |
|
"count": 64132, |
|
"self": 1550.2876053352452, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 138.0882558119415, |
|
"count": 64132, |
|
"self": 5.002939078945474, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 133.08531673299603, |
|
"count": 62547, |
|
"self": 133.08531673299603 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.896670526876278, |
|
"count": 64132, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2324.9156480530255, |
|
"count": 64132, |
|
"is_parallel": true, |
|
"self": 900.3365281020579, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.00232616399989638, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007635090000803757, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0015626549998160044, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0015626549998160044 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.0494281989999763, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006161490005069936, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005685619998985203, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005685619998985203 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04647463799983598, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04647463799983598 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0017688499997348117, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003642489991761977, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001404601000558614, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001404601000558614 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1424.5791199509677, |
|
"count": 64131, |
|
"is_parallel": true, |
|
"self": 36.04246726182009, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 27.113982828087046, |
|
"count": 64131, |
|
"is_parallel": true, |
|
"self": 27.113982828087046 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1254.0565650239932, |
|
"count": 64131, |
|
"is_parallel": true, |
|
"self": 1254.0565650239932 |
|
}, |
|
"steps_from_proto": { |
|
"total": 107.36610483706727, |
|
"count": 64131, |
|
"is_parallel": true, |
|
"self": 22.028856145284863, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 85.3372486917824, |
|
"count": 513048, |
|
"is_parallel": true, |
|
"self": 85.3372486917824 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 635.5062370869064, |
|
"count": 64132, |
|
"self": 2.8657218089792877, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 133.77853596793148, |
|
"count": 64132, |
|
"self": 133.52247146993204, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.2560644979994322, |
|
"count": 2, |
|
"self": 0.2560644979994322 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 498.8619793099956, |
|
"count": 457, |
|
"self": 291.92605036701207, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 206.93592894298354, |
|
"count": 22803, |
|
"self": 206.93592894298354 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.356000211671926e-06, |
|
"count": 1, |
|
"self": 1.356000211671926e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.13396079399990413, |
|
"count": 1, |
|
"self": 0.00197820999983378, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.13198258400007035, |
|
"count": 1, |
|
"self": 0.13198258400007035 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |