|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.3972097337245941, |
|
"min": 0.38621944189071655, |
|
"max": 1.4901529550552368, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 11903.5810546875, |
|
"min": 11512.4287109375, |
|
"max": 45205.28125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989994.0, |
|
"min": 29952.0, |
|
"max": 989994.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989994.0, |
|
"min": 29952.0, |
|
"max": 989994.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.6671622395515442, |
|
"min": -0.10937762260437012, |
|
"max": 0.6671622395515442, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 186.1382598876953, |
|
"min": -26.36000633239746, |
|
"max": 186.1382598876953, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.016319280490279198, |
|
"min": 0.0038585136644542217, |
|
"max": 0.4945586621761322, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 4.553079128265381, |
|
"min": 1.0225061178207397, |
|
"max": 117.21040344238281, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06976626787750884, |
|
"min": 0.06412835257721046, |
|
"max": 0.07501624064508568, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.0464940181626325, |
|
"min": 0.47913735269651825, |
|
"max": 1.0499409684174072, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.01472444731785514, |
|
"min": 0.00036158445444678774, |
|
"max": 0.016693490599011974, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.2208667097678271, |
|
"min": 0.002892675635574302, |
|
"max": 0.2504023589851796, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.517497494200002e-06, |
|
"min": 7.517497494200002e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00011276246241300004, |
|
"min": 0.00011276246241300004, |
|
"max": 0.0031367357544215, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10250580000000001, |
|
"min": 0.10250580000000001, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.537587, |
|
"min": 1.3691136000000002, |
|
"max": 2.4022398, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00026032942000000006, |
|
"min": 0.00026032942000000006, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0039049413000000013, |
|
"min": 0.0039049413000000013, |
|
"max": 0.10458329215000002, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.01543550007045269, |
|
"min": 0.01543550007045269, |
|
"max": 0.4876805245876312, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.2315324991941452, |
|
"min": 0.21735861897468567, |
|
"max": 3.4137637615203857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 289.8453608247423, |
|
"min": 287.6862745098039, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 28115.0, |
|
"min": 15984.0, |
|
"max": 33698.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.6869666522058349, |
|
"min": -1.0000000521540642, |
|
"max": 1.7128155202541537, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 161.94879861176014, |
|
"min": -32.000001668930054, |
|
"max": 176.41999858617783, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.6869666522058349, |
|
"min": -1.0000000521540642, |
|
"max": 1.7128155202541537, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 161.94879861176014, |
|
"min": -32.000001668930054, |
|
"max": 176.41999858617783, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.046886004660336766, |
|
"min": 0.04658305124341266, |
|
"max": 9.160214353352785, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 4.50105644739233, |
|
"min": 4.50105644739233, |
|
"max": 146.56342965364456, |
|
"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": "1681694412", |
|
"python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", |
|
"command_line_arguments": "/home/ark/.miniconda3/envs/deep-rl/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics", |
|
"mlagents_version": "0.31.0.dev0", |
|
"mlagents_envs_version": "0.31.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.11.0+cu113", |
|
"numpy_version": "1.21.2", |
|
"end_time_seconds": "1681695275" |
|
}, |
|
"total": 863.8207598909503, |
|
"count": 1, |
|
"self": 0.21892772300634533, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.013565649976953864, |
|
"count": 1, |
|
"self": 0.013565649976953864 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 863.588266517967, |
|
"count": 1, |
|
"self": 1.02217276499141, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 3.0844673480605707, |
|
"count": 1, |
|
"self": 3.0844673480605707 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 859.4258443419822, |
|
"count": 63891, |
|
"self": 0.9305828708456829, |
|
"children": { |
|
"env_step": { |
|
"total": 523.593627582537, |
|
"count": 63891, |
|
"self": 451.6764727254631, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 71.3016435195459, |
|
"count": 63891, |
|
"self": 2.5283645293675363, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 68.77327899017837, |
|
"count": 62560, |
|
"self": 68.77327899017837 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.6155113375280052, |
|
"count": 63891, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 862.3304329393432, |
|
"count": 63891, |
|
"is_parallel": true, |
|
"self": 467.7116868804442, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.000987220904789865, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0002681976184248924, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0007190232863649726, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0007190232863649726 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.02616152190603316, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00024496298283338547, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0002284129150211811, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0002284129150211811 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.02500095299910754, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.02500095299910754 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0006871930090710521, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00016315095126628876, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0005240420578047633, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0005240420578047633 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 394.618746058899, |
|
"count": 63890, |
|
"is_parallel": true, |
|
"self": 14.385526285273954, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 9.484798599267378, |
|
"count": 63890, |
|
"is_parallel": true, |
|
"self": 9.484798599267378 |
|
}, |
|
"communicator.exchange": { |
|
"total": 330.57257517124526, |
|
"count": 63890, |
|
"is_parallel": true, |
|
"self": 330.57257517124526 |
|
}, |
|
"steps_from_proto": { |
|
"total": 40.17584600311238, |
|
"count": 63890, |
|
"is_parallel": true, |
|
"self": 9.078739975113422, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 31.09710602799896, |
|
"count": 511120, |
|
"is_parallel": true, |
|
"self": 31.09710602799896 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 334.90163388859946, |
|
"count": 63891, |
|
"self": 1.9387582843191922, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 60.89321308792569, |
|
"count": 63891, |
|
"self": 60.767905078828335, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.12530800909735262, |
|
"count": 2, |
|
"self": 0.12530800909735262 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 272.0696625163546, |
|
"count": 438, |
|
"self": 165.02627593895886, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 107.04338657739572, |
|
"count": 22827, |
|
"self": 107.04338657739572 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 7.009366527199745e-07, |
|
"count": 1, |
|
"self": 7.009366527199745e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.05578136199619621, |
|
"count": 1, |
|
"self": 0.0007936309557408094, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.0549877310404554, |
|
"count": 1, |
|
"self": 0.0549877310404554 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |