|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.1545298844575882, |
|
"min": 0.14487138390541077, |
|
"max": 1.4478065967559814, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 4705.1259765625, |
|
"min": 4288.19287109375, |
|
"max": 43920.66015625, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 2999962.0, |
|
"min": 29952.0, |
|
"max": 2999962.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 2999962.0, |
|
"min": 29952.0, |
|
"max": 2999962.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.8651622533798218, |
|
"min": -0.10480409860610962, |
|
"max": 0.8841119408607483, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 266.469970703125, |
|
"min": -25.467395782470703, |
|
"max": 268.2238464355469, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.01823974959552288, |
|
"min": -0.007011605426669121, |
|
"max": 0.5194798707962036, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 5.617843151092529, |
|
"min": -2.075435161590576, |
|
"max": 124.51943969726562, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06750972331653993, |
|
"min": 0.06440509073612351, |
|
"max": 0.07405085455199846, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.945136126431559, |
|
"min": 0.4923244847159367, |
|
"max": 1.0830642637059402, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.015388585903565401, |
|
"min": 6.453619929498871e-05, |
|
"max": 0.018165371629403404, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.21544020264991562, |
|
"min": 0.000903506790129842, |
|
"max": 0.27248057444105106, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 1.523613777876188e-06, |
|
"min": 1.523613777876188e-06, |
|
"max": 0.00029838354339596195, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 2.1330592890266634e-05, |
|
"min": 2.1330592890266634e-05, |
|
"max": 0.004010899663033466, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.1005078380952381, |
|
"min": 0.1005078380952381, |
|
"max": 0.19946118095238097, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4071097333333333, |
|
"min": 1.3962282666666668, |
|
"max": 2.7369665333333337, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 6.073302571428565e-05, |
|
"min": 6.073302571428565e-05, |
|
"max": 0.009946171977142856, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0008502623599999991, |
|
"min": 0.0008502623599999991, |
|
"max": 0.13370295668, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.00838124193251133, |
|
"min": 0.00811163242906332, |
|
"max": 0.722732663154602, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.11733739078044891, |
|
"min": 0.11356285959482193, |
|
"max": 5.059128761291504, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 223.46478873239437, |
|
"min": 204.40845070422534, |
|
"max": 999.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 31732.0, |
|
"min": 15984.0, |
|
"max": 33087.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.7483605501097692, |
|
"min": -1.0000000521540642, |
|
"max": 1.7955915334988648, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 248.26719811558723, |
|
"min": -29.98920151591301, |
|
"max": 254.9739977568388, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.7483605501097692, |
|
"min": -1.0000000521540642, |
|
"max": 1.7955915334988648, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 248.26719811558723, |
|
"min": -29.98920151591301, |
|
"max": 254.9739977568388, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.019456846356673926, |
|
"min": 0.0181169858991216, |
|
"max": 15.741784621030092, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.7628721826476976, |
|
"min": 2.37493149486545, |
|
"max": 251.86855393648148, |
|
"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": "1679934652", |
|
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", |
|
"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": "0.31.0.dev0", |
|
"mlagents_envs_version": "0.31.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.11.0+cu102", |
|
"numpy_version": "1.21.2", |
|
"end_time_seconds": "1679941726" |
|
}, |
|
"total": 7074.304308379, |
|
"count": 1, |
|
"self": 0.4914355529999739, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.12111765200000946, |
|
"count": 1, |
|
"self": 0.12111765200000946 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 7073.691755174, |
|
"count": 1, |
|
"self": 4.465371082887032, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 10.242906995999988, |
|
"count": 1, |
|
"self": 10.242906995999988 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 7058.888956403113, |
|
"count": 194958, |
|
"self": 4.593879521400595, |
|
"children": { |
|
"env_step": { |
|
"total": 5199.395420368696, |
|
"count": 194958, |
|
"self": 4866.331728341763, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 330.3681129019975, |
|
"count": 194958, |
|
"self": 14.356998805771184, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 316.0111140962263, |
|
"count": 187568, |
|
"self": 316.0111140962263 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 2.6955791249361027, |
|
"count": 194958, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 7058.669024681076, |
|
"count": 194958, |
|
"is_parallel": true, |
|
"self": 2543.384661940063, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.005008815999985927, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0036000399999238653, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001408776000062062, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001408776000062062 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04529550300003393, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005295560000604382, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004406209999956445, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004406209999956445 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04278591000002052, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04278591000002052 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0015394159999573276, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00034641199999896344, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011930039999583641, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011930039999583641 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 4515.284362741013, |
|
"count": 194957, |
|
"is_parallel": true, |
|
"self": 93.76680633408978, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 67.15718588593364, |
|
"count": 194957, |
|
"is_parallel": true, |
|
"self": 67.15718588593364 |
|
}, |
|
"communicator.exchange": { |
|
"total": 4076.0676329978705, |
|
"count": 194957, |
|
"is_parallel": true, |
|
"self": 4076.0676329978705 |
|
}, |
|
"steps_from_proto": { |
|
"total": 278.2927375231197, |
|
"count": 194957, |
|
"is_parallel": true, |
|
"self": 60.10413034132222, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 218.18860718179747, |
|
"count": 1559656, |
|
"is_parallel": true, |
|
"self": 218.18860718179747 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 1854.8996565130165, |
|
"count": 194958, |
|
"self": 8.459839935334458, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 355.6127789716951, |
|
"count": 194958, |
|
"self": 354.90408553969485, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.7086934320002456, |
|
"count": 6, |
|
"self": 0.7086934320002456 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1490.827037605987, |
|
"count": 1399, |
|
"self": 947.1703722339637, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 543.6566653720233, |
|
"count": 68394, |
|
"self": 543.6566653720233 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0119993021362461e-06, |
|
"count": 1, |
|
"self": 1.0119993021362461e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.0945196800003032, |
|
"count": 1, |
|
"self": 0.0013677150009243633, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09315196499937883, |
|
"count": 1, |
|
"self": 0.09315196499937883 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |