|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.13484309613704681, |
|
"min": 0.13255511224269867, |
|
"max": 1.4715614318847656, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 4079.8125, |
|
"min": 3946.9609375, |
|
"max": 44641.2890625, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 2999934.0, |
|
"min": 29952.0, |
|
"max": 2999934.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 2999934.0, |
|
"min": 29952.0, |
|
"max": 2999934.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.801253080368042, |
|
"min": -0.11023728549480438, |
|
"max": 0.8468865752220154, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 244.38218688964844, |
|
"min": -26.126235961914062, |
|
"max": 261.1581726074219, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.01356786210089922, |
|
"min": -0.03086991049349308, |
|
"max": 0.3554634749889374, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 4.138197898864746, |
|
"min": -8.365745544433594, |
|
"max": 84.24484252929688, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06996008481387524, |
|
"min": 0.06292635622163335, |
|
"max": 0.07445767317658566, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.0494012722081285, |
|
"min": 0.46839485366945155, |
|
"max": 1.0970733698923139, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.015125260608300441, |
|
"min": 0.0013127453142280992, |
|
"max": 0.017222367379526118, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.22687890912450662, |
|
"min": 0.014108472776027866, |
|
"max": 0.25053178836242296, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 1.5121194959933316e-06, |
|
"min": 1.5121194959933316e-06, |
|
"max": 0.00029838354339596195, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 2.2681792439899973e-05, |
|
"min": 2.2681792439899973e-05, |
|
"max": 0.004027228257590632, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10050400666666666, |
|
"min": 0.10050400666666666, |
|
"max": 0.19946118095238097, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5075600999999998, |
|
"min": 1.3962282666666668, |
|
"max": 2.8424093666666668, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 6.035026599999994e-05, |
|
"min": 6.035026599999994e-05, |
|
"max": 0.009946171977142856, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0009052539899999991, |
|
"min": 0.0009052539899999991, |
|
"max": 0.13425669573, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.008564097806811333, |
|
"min": 0.00841474998742342, |
|
"max": 0.38969168066978455, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.12846146523952484, |
|
"min": 0.11780649423599243, |
|
"max": 2.727841854095459, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 216.86805555555554, |
|
"min": 209.08333333333334, |
|
"max": 999.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 31229.0, |
|
"min": 15984.0, |
|
"max": 33039.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.7822237635825897, |
|
"min": -1.0000000521540642, |
|
"max": 1.7881167812721572, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 254.85799819231033, |
|
"min": -30.559001743793488, |
|
"max": 262.56799817085266, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.7822237635825897, |
|
"min": -1.0000000521540642, |
|
"max": 1.7881167812721572, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 254.85799819231033, |
|
"min": -30.559001743793488, |
|
"max": 262.56799817085266, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.019242743338998898, |
|
"min": 0.018860102466922917, |
|
"max": 7.597729445435107, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.7517122974768427, |
|
"min": 2.508393628100748, |
|
"max": 121.56367112696171, |
|
"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": "1660980358", |
|
"python_version": "3.9.7 | packaged by conda-forge | (default, Sep 29 2021, 19:23:11) \n[GCC 9.4.0]", |
|
"command_line_arguments": "/home/studio-lab-user/.conda/envs/d2l/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training2 --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": "1.21.4", |
|
"end_time_seconds": "1660985715" |
|
}, |
|
"total": 5357.028527222, |
|
"count": 1, |
|
"self": 0.3207162340004288, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.07508762400016167, |
|
"count": 1, |
|
"self": 0.07508762400016167 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 5356.6327233639995, |
|
"count": 1, |
|
"self": 3.5570683310452296, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 9.231680407000113, |
|
"count": 1, |
|
"self": 9.231680407000113 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 5343.752470810954, |
|
"count": 195431, |
|
"self": 3.5716219709247525, |
|
"children": { |
|
"env_step": { |
|
"total": 3451.897419213865, |
|
"count": 195431, |
|
"self": 3164.6863409240223, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 285.05936036884873, |
|
"count": 195431, |
|
"self": 13.534244142049147, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 271.5251162267996, |
|
"count": 187573, |
|
"self": 88.17436237970378, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 183.3507538470958, |
|
"count": 187573, |
|
"self": 183.3507538470958 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 2.1517179209938604, |
|
"count": 195431, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 5348.999863559679, |
|
"count": 195431, |
|
"is_parallel": true, |
|
"self": 2434.9059987708597, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0035244210000655585, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0019902950004961895, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001534125999569369, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001534125999569369 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.03743287900010728, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00034319700012019894, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0002939920000244456, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0002939920000244456 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.03574911199984854, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.03574911199984854 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0010465780001140956, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0002887999999074964, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0007577780002065992, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0007577780002065992 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 2914.0938647888197, |
|
"count": 195430, |
|
"is_parallel": true, |
|
"self": 67.43264153396467, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 46.074633980849285, |
|
"count": 195430, |
|
"is_parallel": true, |
|
"self": 46.074633980849285 |
|
}, |
|
"communicator.exchange": { |
|
"total": 2596.2725378499445, |
|
"count": 195430, |
|
"is_parallel": true, |
|
"self": 2596.2725378499445 |
|
}, |
|
"steps_from_proto": { |
|
"total": 204.31405142406106, |
|
"count": 195430, |
|
"is_parallel": true, |
|
"self": 49.94330426554234, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 154.37074715851872, |
|
"count": 1563440, |
|
"is_parallel": true, |
|
"self": 154.37074715851872 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 1888.2834296261642, |
|
"count": 195431, |
|
"self": 7.22656501701681, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 418.3046924581438, |
|
"count": 195431, |
|
"self": 417.7316452461439, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.5730472119998922, |
|
"count": 6, |
|
"self": 0.5730472119998922 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1462.7521721510036, |
|
"count": 1397, |
|
"self": 585.1648097449454, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 877.5873624060582, |
|
"count": 68418, |
|
"self": 877.5873624060582 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0390003808424808e-06, |
|
"count": 1, |
|
"self": 1.0390003808424808e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09150277600019763, |
|
"count": 1, |
|
"self": 0.0008970120006779325, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.0906057639995197, |
|
"count": 1, |
|
"self": 0.0906057639995197 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |