|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.5224190354347229, |
|
"min": 0.49271532893180847, |
|
"max": 1.439494252204895, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 15689.2890625, |
|
"min": 14749.92578125, |
|
"max": 43668.49609375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989983.0, |
|
"min": 29952.0, |
|
"max": 989983.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989983.0, |
|
"min": 29952.0, |
|
"max": 989983.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.2036179006099701, |
|
"min": -0.14107874035835266, |
|
"max": 0.21507544815540314, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 50.904476165771484, |
|
"min": -33.999977111816406, |
|
"max": 54.62916564941406, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.018383555114269257, |
|
"min": -0.018383555114269257, |
|
"max": 0.251579612493515, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -4.595888614654541, |
|
"min": -4.595888614654541, |
|
"max": 60.63068389892578, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06536446034026865, |
|
"min": 0.0642009889466775, |
|
"max": 0.0728767210123887, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.915102444763761, |
|
"min": 0.49691030921229834, |
|
"max": 1.0612286676090055, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.008953100920648252, |
|
"min": 0.00010143903598362831, |
|
"max": 0.009994440046457817, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.12534341288907552, |
|
"min": 0.001318707467787168, |
|
"max": 0.13992216065040944, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.729811709142855e-06, |
|
"min": 7.729811709142855e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010821736392799997, |
|
"min": 0.00010821736392799997, |
|
"max": 0.003141333252889, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10257657142857145, |
|
"min": 0.10257657142857145, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4360720000000002, |
|
"min": 1.3886848, |
|
"max": 2.3471110000000004, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00026739948571428567, |
|
"min": 0.00026739948571428567, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003743592799999999, |
|
"min": 0.003743592799999999, |
|
"max": 0.10473638889999999, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.012773019261658192, |
|
"min": 0.012773019261658192, |
|
"max": 0.4229970872402191, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.17882226407527924, |
|
"min": 0.17882226407527924, |
|
"max": 2.960979700088501, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 714.375, |
|
"min": 625.4313725490196, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 28575.0, |
|
"min": 15984.0, |
|
"max": 33409.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 0.6354599686339497, |
|
"min": -1.0000000521540642, |
|
"max": 0.9038038823534461, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 25.41839874535799, |
|
"min": -30.996401615440845, |
|
"max": 46.09399800002575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 0.6354599686339497, |
|
"min": -1.0000000521540642, |
|
"max": 0.9038038823534461, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 25.41839874535799, |
|
"min": -30.996401615440845, |
|
"max": 46.09399800002575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.09395440032458283, |
|
"min": 0.08643259735111439, |
|
"max": 8.468636597506702, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.758176012983313, |
|
"min": 3.758176012983313, |
|
"max": 135.49818556010723, |
|
"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": "1677595823", |
|
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0", |
|
"mlagents_envs_version": "0.29.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.8.1+cu102", |
|
"numpy_version": "1.22.4", |
|
"end_time_seconds": "1677598011" |
|
}, |
|
"total": 2188.06026035, |
|
"count": 1, |
|
"self": 0.48934516500003156, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.10384097799999381, |
|
"count": 1, |
|
"self": 0.10384097799999381 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2187.467074207, |
|
"count": 1, |
|
"self": 1.5469988189720425, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.139557065999952, |
|
"count": 1, |
|
"self": 6.139557065999952 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2179.6911556460277, |
|
"count": 63249, |
|
"self": 1.6552617449447098, |
|
"children": { |
|
"env_step": { |
|
"total": 1444.0072555749946, |
|
"count": 63249, |
|
"self": 1324.1705971178662, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 118.92942623108536, |
|
"count": 63249, |
|
"self": 4.859671599078752, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 114.0697546320066, |
|
"count": 62571, |
|
"self": 38.55037076895337, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 75.51938386305324, |
|
"count": 62571, |
|
"self": 75.51938386305324 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.9072322260431065, |
|
"count": 63249, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2182.5036594499356, |
|
"count": 63249, |
|
"is_parallel": true, |
|
"self": 978.5472273618802, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0018198960000290754, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006698280000136947, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011500680000153807, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011500680000153807 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.047563867999997456, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005090610000024753, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004389169999967635, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004389169999967635 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04501371399999243, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04501371399999243 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0016021760000057839, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00039449499990951153, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012076810000962723, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012076810000962723 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1203.9564320880554, |
|
"count": 63248, |
|
"is_parallel": true, |
|
"self": 31.76276381804314, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 22.99022920402831, |
|
"count": 63248, |
|
"is_parallel": true, |
|
"self": 22.99022920402831 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1056.2213445149846, |
|
"count": 63248, |
|
"is_parallel": true, |
|
"self": 1056.2213445149846 |
|
}, |
|
"steps_from_proto": { |
|
"total": 92.98209455099936, |
|
"count": 63248, |
|
"is_parallel": true, |
|
"self": 22.59487503204946, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 70.3872195189499, |
|
"count": 505984, |
|
"is_parallel": true, |
|
"self": 70.3872195189499 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 734.0286383260884, |
|
"count": 63249, |
|
"self": 2.7723440811013234, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 161.0962124739857, |
|
"count": 63249, |
|
"self": 160.86030770298578, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.23590477099992313, |
|
"count": 2, |
|
"self": 0.23590477099992313 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 570.1600817710014, |
|
"count": 436, |
|
"self": 219.7357181799938, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 350.4243635910076, |
|
"count": 22854, |
|
"self": 350.4243635910076 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.360002539120615e-07, |
|
"count": 1, |
|
"self": 8.360002539120615e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08936184000003777, |
|
"count": 1, |
|
"self": 0.0018566339999779302, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.08750520600005984, |
|
"count": 1, |
|
"self": 0.08750520600005984 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |