|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.5555771589279175, |
|
"min": 0.5555771589279175, |
|
"max": 1.3511556386947632, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 16533.9765625, |
|
"min": 16533.9765625, |
|
"max": 40988.65625, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989950.0, |
|
"min": 29952.0, |
|
"max": 989950.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989950.0, |
|
"min": 29952.0, |
|
"max": 989950.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.13370367884635925, |
|
"min": -0.10792555660009384, |
|
"max": 0.18158511817455292, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 33.55962371826172, |
|
"min": -26.010059356689453, |
|
"max": 45.941036224365234, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.005116866901516914, |
|
"min": -0.005071492865681648, |
|
"max": 0.29099249839782715, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 1.28433358669281, |
|
"min": -1.25773024559021, |
|
"max": 68.96522521972656, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.04412110306937912, |
|
"min": 0.04412110306937912, |
|
"max": 0.05179467467004339, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.6176954429713077, |
|
"min": 0.3625627226903037, |
|
"max": 0.7059182961264419, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.0075576953130231635, |
|
"min": 0.0002963896903985677, |
|
"max": 0.011014831698115332, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.10580773438232428, |
|
"min": 0.0038530659751813807, |
|
"max": 0.11891083483351396, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.222319021164285e-06, |
|
"min": 7.222319021164285e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.0001011124662963, |
|
"min": 0.0001011124662963, |
|
"max": 0.0035081342306219994, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10240740714285712, |
|
"min": 0.10240740714285712, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4337036999999997, |
|
"min": 1.3886848, |
|
"max": 2.569378, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.000491240687857143, |
|
"min": 0.000491240687857143, |
|
"max": 0.019676870217142855, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.006877369630000002, |
|
"min": 0.006877369630000002, |
|
"max": 0.2338986622, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.010875050909817219, |
|
"min": 0.010875050909817219, |
|
"max": 0.5158635377883911, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.15225070714950562, |
|
"min": 0.15225070714950562, |
|
"max": 3.6110448837280273, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 724.4878048780488, |
|
"min": 673.8666666666667, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29704.0, |
|
"min": 15984.0, |
|
"max": 32686.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 0.4947511893583507, |
|
"min": -1.0000000521540642, |
|
"max": 0.6592444040709071, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 20.28479876369238, |
|
"min": -30.514801643788815, |
|
"max": 29.665998183190823, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 0.4947511893583507, |
|
"min": -1.0000000521540642, |
|
"max": 0.6592444040709071, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 20.28479876369238, |
|
"min": -30.514801643788815, |
|
"max": 29.665998183190823, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.1651188201184396, |
|
"min": 0.1591329200620142, |
|
"max": 21.3197267241776, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 6.769871624856023, |
|
"min": 6.769871624856023, |
|
"max": 341.1156275868416, |
|
"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": "1700922570", |
|
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", |
|
"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": "1.1.0.dev0", |
|
"mlagents_envs_version": "1.1.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "2.1.0+cu118", |
|
"numpy_version": "1.23.5", |
|
"end_time_seconds": "1700924950" |
|
}, |
|
"total": 2379.785221288, |
|
"count": 1, |
|
"self": 0.4762838050000937, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.08426403199996457, |
|
"count": 1, |
|
"self": 0.08426403199996457 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2379.224673451, |
|
"count": 1, |
|
"self": 1.7398534759627182, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 8.880418856000006, |
|
"count": 1, |
|
"self": 8.880418856000006 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2368.526796672037, |
|
"count": 63256, |
|
"self": 1.7748473900987847, |
|
"children": { |
|
"env_step": { |
|
"total": 1561.87138197193, |
|
"count": 63256, |
|
"self": 1403.8413400508862, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 156.9797802110196, |
|
"count": 63256, |
|
"self": 5.232784402007383, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 151.74699580901222, |
|
"count": 62558, |
|
"self": 151.74699580901222 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 1.0502617100241878, |
|
"count": 63256, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2373.85237076398, |
|
"count": 63256, |
|
"is_parallel": true, |
|
"self": 1110.5320144279963, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.004845638000006147, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0034575689998064263, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001388069000199721, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001388069000199721 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.09867285399991488, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006190619998278635, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.000484259000018028, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000484259000018028 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.0957939490000399, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0957939490000399 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0017755840000290846, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003598540000666617, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0014157299999624229, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0014157299999624229 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1263.320356335984, |
|
"count": 63255, |
|
"is_parallel": true, |
|
"self": 38.128328791952754, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 26.64825646602071, |
|
"count": 63255, |
|
"is_parallel": true, |
|
"self": 26.64825646602071 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1088.3408103369848, |
|
"count": 63255, |
|
"is_parallel": true, |
|
"self": 1088.3408103369848 |
|
}, |
|
"steps_from_proto": { |
|
"total": 110.20296074102555, |
|
"count": 63255, |
|
"is_parallel": true, |
|
"self": 23.23439513398307, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 86.96856560704248, |
|
"count": 506040, |
|
"is_parallel": true, |
|
"self": 86.96856560704248 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 804.8805673100082, |
|
"count": 63256, |
|
"self": 3.182003762995919, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 136.600109983013, |
|
"count": 63256, |
|
"self": 136.3887323480128, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.2113776350001899, |
|
"count": 2, |
|
"self": 0.2113776350001899 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 665.0984535639993, |
|
"count": 446, |
|
"self": 465.9359561330024, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 199.16249743099695, |
|
"count": 18755, |
|
"self": 199.16249743099695 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.479999789618887e-07, |
|
"count": 1, |
|
"self": 9.479999789618887e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.07760349899990615, |
|
"count": 1, |
|
"self": 0.0014059569998607913, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.07619754200004536, |
|
"count": 1, |
|
"self": 0.07619754200004536 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |