|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.4478599727153778, |
|
"min": 0.43328985571861267, |
|
"max": 1.4866670370101929, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 13579.1142578125, |
|
"min": 12970.96484375, |
|
"max": 45099.53125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989952.0, |
|
"min": 29952.0, |
|
"max": 989952.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989952.0, |
|
"min": 29952.0, |
|
"max": 989952.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.5806148648262024, |
|
"min": -0.12018542736768723, |
|
"max": 0.6390016674995422, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 161.4109344482422, |
|
"min": -28.483945846557617, |
|
"max": 180.19847106933594, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.017999060451984406, |
|
"min": -0.08266350626945496, |
|
"max": 0.23121079802513123, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 5.003738880157471, |
|
"min": -23.641761779785156, |
|
"max": 55.7218017578125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.07010516601925096, |
|
"min": 0.06312016568791334, |
|
"max": 0.07413867955929725, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9814723242695135, |
|
"min": 0.49650481771497085, |
|
"max": 1.0774681558153436, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.014394051328140664, |
|
"min": 0.0007263853829974161, |
|
"max": 0.015379924125976259, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.2015167185939693, |
|
"min": 0.007263853829974161, |
|
"max": 0.2306988618896439, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.409668958714288e-06, |
|
"min": 7.409668958714288e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010373536542200004, |
|
"min": 0.00010373536542200004, |
|
"max": 0.0035070254309915996, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10246985714285714, |
|
"min": 0.10246985714285714, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.434578, |
|
"min": 1.3886848, |
|
"max": 2.5724676, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00025673872857142867, |
|
"min": 0.00025673872857142867, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0035943422000000017, |
|
"min": 0.0035943422000000017, |
|
"max": 0.11692393915999999, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.007644892204552889, |
|
"min": 0.007644892204552889, |
|
"max": 0.36405229568481445, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.10702849179506302, |
|
"min": 0.10702849179506302, |
|
"max": 2.548366069793701, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 332.6489361702128, |
|
"min": 308.7448979591837, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 31269.0, |
|
"min": 15984.0, |
|
"max": 33201.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.646065943735711, |
|
"min": -1.0000000521540642, |
|
"max": 1.6762708127498627, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 154.73019871115685, |
|
"min": -32.000001668930054, |
|
"max": 163.3287976682186, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.646065943735711, |
|
"min": -1.0000000521540642, |
|
"max": 1.6762708127498627, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 154.73019871115685, |
|
"min": -32.000001668930054, |
|
"max": 163.3287976682186, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.026133982572881652, |
|
"min": 0.025216861234311896, |
|
"max": 7.258660348132253, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.4565943618508754, |
|
"min": 2.3451680947910063, |
|
"max": 116.13856557011604, |
|
"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": "1673759115", |
|
"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": "1673761276" |
|
}, |
|
"total": 2161.245086303, |
|
"count": 1, |
|
"self": 0.44182907899948987, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.11144154000021445, |
|
"count": 1, |
|
"self": 0.11144154000021445 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2160.691815684, |
|
"count": 1, |
|
"self": 1.270914119036206, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.3576437340002485, |
|
"count": 1, |
|
"self": 6.3576437340002485 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2152.969754671964, |
|
"count": 64057, |
|
"self": 1.3048801061013364, |
|
"children": { |
|
"env_step": { |
|
"total": 1462.7152694548968, |
|
"count": 64057, |
|
"self": 1352.7379722059295, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 109.20994353796777, |
|
"count": 64057, |
|
"self": 4.400112500984051, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 104.80983103698372, |
|
"count": 62563, |
|
"self": 35.43719977805995, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 69.37263125892378, |
|
"count": 62563, |
|
"self": 69.37263125892378 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.7673537109994868, |
|
"count": 64057, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2156.279027359093, |
|
"count": 64057, |
|
"is_parallel": true, |
|
"self": 905.7551749431341, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0018472480001037184, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006454789991039434, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001201769000999775, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001201769000999775 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.044126468999820645, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005505859994627826, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005235839998931624, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005235839998931624 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04118885800016869, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04118885800016869 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0018634410002960067, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004317980010455358, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001431642999250471, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001431642999250471 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1250.523852415959, |
|
"count": 64056, |
|
"is_parallel": true, |
|
"self": 28.246456015973763, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 26.091944875039644, |
|
"count": 64056, |
|
"is_parallel": true, |
|
"self": 26.091944875039644 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1088.4077729809633, |
|
"count": 64056, |
|
"is_parallel": true, |
|
"self": 1088.4077729809633 |
|
}, |
|
"steps_from_proto": { |
|
"total": 107.77767854398235, |
|
"count": 64056, |
|
"is_parallel": true, |
|
"self": 23.82944295387142, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 83.94823559011093, |
|
"count": 512448, |
|
"is_parallel": true, |
|
"self": 83.94823559011093 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 688.9496051109659, |
|
"count": 64057, |
|
"self": 2.2628338811264257, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 152.67200073683716, |
|
"count": 64057, |
|
"self": 152.4704065298365, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.20159420700065311, |
|
"count": 2, |
|
"self": 0.20159420700065311 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 534.0147704930023, |
|
"count": 451, |
|
"self": 200.7299172119906, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 333.2848532810117, |
|
"count": 22827, |
|
"self": 333.2848532810117 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.1920001270482317e-06, |
|
"count": 1, |
|
"self": 1.1920001270482317e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09350196699961089, |
|
"count": 1, |
|
"self": 0.0016695179992893827, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.0918324490003215, |
|
"count": 1, |
|
"self": 0.0918324490003215 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |