|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.1519065648317337, |
|
"min": 0.146709606051445, |
|
"max": 1.4485841989517212, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 4532.89208984375, |
|
"min": 4373.1201171875, |
|
"max": 43944.25, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 2999916.0, |
|
"min": 29952.0, |
|
"max": 2999916.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 2999916.0, |
|
"min": 29952.0, |
|
"max": 2999916.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.8808816075325012, |
|
"min": -0.24982436001300812, |
|
"max": 0.8808816075325012, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 263.38360595703125, |
|
"min": -59.2083740234375, |
|
"max": 263.38360595703125, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.0031910657417029142, |
|
"min": -0.06275332719087601, |
|
"max": 0.551007866859436, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 0.9541286826133728, |
|
"min": -18.323970794677734, |
|
"max": 130.5888671875, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06667955407049574, |
|
"min": 0.06213645751579732, |
|
"max": 0.07380040665950446, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9335137569869404, |
|
"min": 0.5166028466165312, |
|
"max": 1.0914608400392658, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.014350790452832978, |
|
"min": 0.0011039727543285683, |
|
"max": 0.015871432327133207, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.2009110663396617, |
|
"min": 0.012143700297614251, |
|
"max": 0.22675631587067163, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 1.543663771192862e-06, |
|
"min": 1.543663771192862e-06, |
|
"max": 0.00029838354339596195, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 2.1611292796700067e-05, |
|
"min": 2.1611292796700067e-05, |
|
"max": 0.004053203448932199, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10051452142857144, |
|
"min": 0.10051452142857144, |
|
"max": 0.19946118095238097, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4072033000000002, |
|
"min": 1.3962282666666668, |
|
"max": 2.8125069, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 6.140069071428589e-05, |
|
"min": 6.140069071428589e-05, |
|
"max": 0.009946171977142856, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0008596096700000024, |
|
"min": 0.0008596096700000024, |
|
"max": 0.13511167322, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.007030579727143049, |
|
"min": 0.006488851271569729, |
|
"max": 0.5527361631393433, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.09842811524868011, |
|
"min": 0.09084391593933105, |
|
"max": 3.8691532611846924, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 203.14285714285714, |
|
"min": 203.14285714285714, |
|
"max": 999.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 27018.0, |
|
"min": 15984.0, |
|
"max": 32681.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.781812019534129, |
|
"min": -1.0000000521540642, |
|
"max": 1.7917625759359743, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 236.98099859803915, |
|
"min": -30.71260165423155, |
|
"max": 249.05499805510044, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.781812019534129, |
|
"min": -1.0000000521540642, |
|
"max": 1.7917625759359743, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 236.98099859803915, |
|
"min": -30.71260165423155, |
|
"max": 249.05499805510044, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.014713893364633511, |
|
"min": 0.014713893364633511, |
|
"max": 10.769489921629429, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 1.956947817496257, |
|
"min": 1.956947817496257, |
|
"max": 172.31183874607086, |
|
"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": "1663652908", |
|
"python_version": "3.7.14 (default, Sep 8 2022, 00:06:44) \n[GCC 7.5.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-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": "1663659732" |
|
}, |
|
"total": 6823.655828139001, |
|
"count": 1, |
|
"self": 0.4380322620008883, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.052285955000002104, |
|
"count": 1, |
|
"self": 0.052285955000002104 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 6823.165509922, |
|
"count": 1, |
|
"self": 4.322114260139642, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 10.424575584000024, |
|
"count": 1, |
|
"self": 10.424575584000024 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 6808.32239480286, |
|
"count": 194887, |
|
"self": 4.370861308726489, |
|
"children": { |
|
"env_step": { |
|
"total": 4702.866568041112, |
|
"count": 194887, |
|
"self": 4382.213663380145, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 318.3032546269897, |
|
"count": 194887, |
|
"self": 13.959708231118839, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 304.3435463958709, |
|
"count": 187549, |
|
"self": 104.02258748871799, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 200.32095890715289, |
|
"count": 187549, |
|
"self": 200.32095890715289 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 2.34965003397798, |
|
"count": 194887, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 6810.354721428062, |
|
"count": 194887, |
|
"is_parallel": true, |
|
"self": 2732.7685380851203, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.005749642000012045, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.004516225999964263, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012334160000477823, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012334160000477823 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04576541599999473, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000515414000005876, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00042740700001786536, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00042740700001786536 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04315310699996644, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04315310699996644 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0016694880000045487, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004220439999471637, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001247444000057385, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001247444000057385 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 4077.5861833429412, |
|
"count": 194886, |
|
"is_parallel": true, |
|
"self": 86.08284411611112, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 69.172400512845, |
|
"count": 194886, |
|
"is_parallel": true, |
|
"self": 69.172400512845 |
|
}, |
|
"communicator.exchange": { |
|
"total": 3642.0390962290085, |
|
"count": 194886, |
|
"is_parallel": true, |
|
"self": 3642.0390962290085 |
|
}, |
|
"steps_from_proto": { |
|
"total": 280.2918424849766, |
|
"count": 194886, |
|
"is_parallel": true, |
|
"self": 70.4321200502464, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 209.8597224347302, |
|
"count": 1559088, |
|
"is_parallel": true, |
|
"self": 209.8597224347302 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 2101.0849654530216, |
|
"count": 194887, |
|
"self": 8.188185902986788, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 483.9639206030234, |
|
"count": 194887, |
|
"self": 483.38015089802394, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.5837697049994404, |
|
"count": 6, |
|
"self": 0.5837697049994404 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1608.9328589470115, |
|
"count": 1401, |
|
"self": 634.2073622789515, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 974.72549666806, |
|
"count": 68358, |
|
"self": 974.72549666806 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.1209995136596262e-06, |
|
"count": 1, |
|
"self": 1.1209995136596262e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09642415400048776, |
|
"count": 1, |
|
"self": 0.0016449480008304818, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09477920599965728, |
|
"count": 1, |
|
"self": 0.09477920599965728 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |