|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.4563570022583008, |
|
"min": 0.4563570022583008, |
|
"max": 1.3712244033813477, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 13690.7099609375, |
|
"min": 13690.7099609375, |
|
"max": 41597.46484375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989900.0, |
|
"min": 29902.0, |
|
"max": 989900.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989900.0, |
|
"min": 29902.0, |
|
"max": 989900.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.4900907576084137, |
|
"min": -0.10003183782100677, |
|
"max": 0.5350491404533386, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 135.75514221191406, |
|
"min": -24.10767364501953, |
|
"max": 147.13851928710938, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -1.7200865745544434, |
|
"min": -1.7200865745544434, |
|
"max": 0.37860435247421265, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -476.4639892578125, |
|
"min": -476.4639892578125, |
|
"max": 91.62225341796875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06789637719269931, |
|
"min": 0.06373426844134619, |
|
"max": 0.07273745328704642, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9505492806977903, |
|
"min": 0.509162173009325, |
|
"max": 1.0644539536008901, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.22389991925142352, |
|
"min": 0.0003301194277613202, |
|
"max": 0.25530000823172966, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 3.1345988695199294, |
|
"min": 0.004291552560897163, |
|
"max": 3.5742001152442153, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.627426028985717e-06, |
|
"min": 7.627426028985717e-06, |
|
"max": 0.00029523505873117143, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010678396440580004, |
|
"min": 0.00010678396440580004, |
|
"max": 0.0036323875892041993, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10254244285714287, |
|
"min": 0.10254244285714287, |
|
"max": 0.19841168571428572, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4355942000000002, |
|
"min": 1.3888818, |
|
"max": 2.6107958000000004, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00026399004142857154, |
|
"min": 0.00026399004142857154, |
|
"max": 0.009841327402857142, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0036958605800000016, |
|
"min": 0.0036958605800000016, |
|
"max": 0.12109850041999999, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.017958655953407288, |
|
"min": 0.017417704686522484, |
|
"max": 0.6661913990974426, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.251421183347702, |
|
"min": 0.24384786188602448, |
|
"max": 4.663339614868164, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 360.9642857142857, |
|
"min": 335.4712643678161, |
|
"max": 996.25, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30321.0, |
|
"min": 16573.0, |
|
"max": 32898.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.543778548638026, |
|
"min": -0.9345188008155674, |
|
"max": 1.6082697410223097, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 129.67739808559418, |
|
"min": -30.668201565742493, |
|
"max": 138.31119772791862, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.543778548638026, |
|
"min": -0.9345188008155674, |
|
"max": 1.6082697410223097, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 129.67739808559418, |
|
"min": -30.668201565742493, |
|
"max": 138.31119772791862, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.06720657936377739, |
|
"min": 0.06080380713418973, |
|
"max": 12.387886750347475, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 5.645352666557301, |
|
"min": 5.350735027808696, |
|
"max": 210.59407475590706, |
|
"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": "1676830733", |
|
"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": "1.21.6", |
|
"end_time_seconds": "1676833042" |
|
}, |
|
"total": 2309.461859818, |
|
"count": 1, |
|
"self": 0.9785437209998236, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.4283768470000098, |
|
"count": 1, |
|
"self": 0.4283768470000098 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2308.05493925, |
|
"count": 1, |
|
"self": 1.4065813800384603, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 10.430258385999991, |
|
"count": 1, |
|
"self": 10.430258385999991 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2296.089084341962, |
|
"count": 63611, |
|
"self": 1.5190976119602055, |
|
"children": { |
|
"env_step": { |
|
"total": 1531.9074852420042, |
|
"count": 63611, |
|
"self": 1414.7361031459754, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 116.28988777200806, |
|
"count": 63611, |
|
"self": 4.860381136022738, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 111.42950663598532, |
|
"count": 62562, |
|
"self": 37.24287229394051, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 74.18663434204481, |
|
"count": 62562, |
|
"self": 74.18663434204481 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.881494324020764, |
|
"count": 63611, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2303.167662875041, |
|
"count": 63611, |
|
"is_parallel": true, |
|
"self": 1007.621325726039, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.006433823999998367, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0034557389999747556, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0029780850000236114, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0029780850000236114 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05600995399998965, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005959449999863864, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005258060000130627, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005258060000130627 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.05302472599998964, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.05302472599998964 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0018634770000005574, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004520379999632951, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0014114390000372623, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0014114390000372623 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1295.546337149002, |
|
"count": 63610, |
|
"is_parallel": true, |
|
"self": 32.89332437892563, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 23.341987588986967, |
|
"count": 63610, |
|
"is_parallel": true, |
|
"self": 23.341987588986967 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1142.5407649020522, |
|
"count": 63610, |
|
"is_parallel": true, |
|
"self": 1142.5407649020522 |
|
}, |
|
"steps_from_proto": { |
|
"total": 96.77026027903722, |
|
"count": 63610, |
|
"is_parallel": true, |
|
"self": 22.979666412904663, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 73.79059386613255, |
|
"count": 508880, |
|
"is_parallel": true, |
|
"self": 73.79059386613255 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 762.6625014879975, |
|
"count": 63611, |
|
"self": 2.7692600569994283, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 165.29268561199714, |
|
"count": 63611, |
|
"self": 165.00765446799696, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.28503114400018603, |
|
"count": 2, |
|
"self": 0.28503114400018603 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 594.6005558190009, |
|
"count": 453, |
|
"self": 230.8060464059862, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 363.7945094130147, |
|
"count": 22755, |
|
"self": 363.7945094130147 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.294999947276665e-06, |
|
"count": 1, |
|
"self": 1.294999947276665e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.1290138469998965, |
|
"count": 1, |
|
"self": 0.0019093609998890315, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.12710448600000746, |
|
"count": 1, |
|
"self": 0.12710448600000746 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |