|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.2669830322265625, |
|
"min": 0.2669830322265625, |
|
"max": 1.4712860584259033, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 8043.66455078125, |
|
"min": 8032.3330078125, |
|
"max": 44632.93359375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989944.0, |
|
"min": 29952.0, |
|
"max": 989944.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989944.0, |
|
"min": 29952.0, |
|
"max": 989944.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.5837921500205994, |
|
"min": -0.08212026208639145, |
|
"max": 0.6005130410194397, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 164.04559326171875, |
|
"min": -19.790983200073242, |
|
"max": 168.74417114257812, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.04139707610011101, |
|
"min": 0.0010012340499088168, |
|
"max": 0.5905066132545471, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 11.63257884979248, |
|
"min": 0.2763406038284302, |
|
"max": 139.9500732421875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.0681310610766535, |
|
"min": 0.0655922497116944, |
|
"max": 0.07592057391310582, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9538348550731489, |
|
"min": 0.4874179593405162, |
|
"max": 1.0779755077965094, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.015715340061529623, |
|
"min": 0.0007007067294152112, |
|
"max": 0.01755681665686314, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.22001476086141472, |
|
"min": 0.009109187482397746, |
|
"max": 0.24579543319608396, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.720061712392855e-06, |
|
"min": 7.720061712392855e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010808086397349997, |
|
"min": 0.00010808086397349997, |
|
"max": 0.0036344275885242, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10257332142857142, |
|
"min": 0.10257332142857142, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4360264999999999, |
|
"min": 1.3886848, |
|
"max": 2.6114758, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00026707481071428565, |
|
"min": 0.00026707481071428565, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0037390473499999987, |
|
"min": 0.0037390473499999987, |
|
"max": 0.12116643242, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.010527675971388817, |
|
"min": 0.010527675971388817, |
|
"max": 0.3377474248409271, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.14738745987415314, |
|
"min": 0.14738745987415314, |
|
"max": 2.364232063293457, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 321.90425531914894, |
|
"min": 308.3333333333333, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30259.0, |
|
"min": 15984.0, |
|
"max": 33074.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.6539557731465289, |
|
"min": -1.0000000521540642, |
|
"max": 1.6624318063259125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 157.12579844892025, |
|
"min": -28.48580162972212, |
|
"max": 157.12579844892025, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.6539557731465289, |
|
"min": -1.0000000521540642, |
|
"max": 1.6624318063259125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 157.12579844892025, |
|
"min": -28.48580162972212, |
|
"max": 157.12579844892025, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.07119671024143157, |
|
"min": 0.06987619054048542, |
|
"max": 13.273005364462733, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 6.763687472935999, |
|
"min": 6.218980958103202, |
|
"max": 212.36808583140373, |
|
"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": "1673477690", |
|
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", |
|
"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": "1673479735" |
|
}, |
|
"total": 2044.9227629299999, |
|
"count": 1, |
|
"self": 0.4403693219996967, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.10536214700005075, |
|
"count": 1, |
|
"self": 0.10536214700005075 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2044.3770314610001, |
|
"count": 1, |
|
"self": 1.14091233299132, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 7.309224038999901, |
|
"count": 1, |
|
"self": 7.309224038999901 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2035.8337039770088, |
|
"count": 64021, |
|
"self": 1.1588700420809346, |
|
"children": { |
|
"env_step": { |
|
"total": 1374.3727348129921, |
|
"count": 64021, |
|
"self": 1275.834502515007, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 97.83902520899528, |
|
"count": 64021, |
|
"self": 4.1200234240477585, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 93.71900178494752, |
|
"count": 62546, |
|
"self": 31.849082573977967, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 61.869919210969556, |
|
"count": 62546, |
|
"self": 61.869919210969556 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.6992070889898514, |
|
"count": 64021, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2041.3237545401028, |
|
"count": 64021, |
|
"is_parallel": true, |
|
"self": 860.1112856470672, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.005118559000038658, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0029453369998009293, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.002173222000237729, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.002173222000237729 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04712530599999809, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004891369999313611, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.000434877000088818, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000434877000088818 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.044655059999968216, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.044655059999968216 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0015462320000096952, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003957100004754466, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011505219995342486, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011505219995342486 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1181.2124688930355, |
|
"count": 64020, |
|
"is_parallel": true, |
|
"self": 27.148797815958915, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 21.389607497971383, |
|
"count": 64020, |
|
"is_parallel": true, |
|
"self": 21.389607497971383 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1043.6281492500607, |
|
"count": 64020, |
|
"is_parallel": true, |
|
"self": 1043.6281492500607 |
|
}, |
|
"steps_from_proto": { |
|
"total": 89.04591432904454, |
|
"count": 64020, |
|
"is_parallel": true, |
|
"self": 20.302686508069428, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 68.74322782097511, |
|
"count": 512160, |
|
"is_parallel": true, |
|
"self": 68.74322782097511 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 660.3020991219357, |
|
"count": 64021, |
|
"self": 2.1996471979459784, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 142.81134409399328, |
|
"count": 64021, |
|
"self": 142.34968986999365, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.46165422399963063, |
|
"count": 5, |
|
"self": 0.46165422399963063 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 515.2911078299965, |
|
"count": 456, |
|
"self": 198.71917869297, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 316.5719291370265, |
|
"count": 22833, |
|
"self": 316.5719291370265 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.229999366449192e-07, |
|
"count": 1, |
|
"self": 8.229999366449192e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09319028900017656, |
|
"count": 1, |
|
"self": 0.0013276460003908142, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09186264299978575, |
|
"count": 1, |
|
"self": 0.09186264299978575 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |