|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.22811010479927063, |
|
"min": 0.2168775498867035, |
|
"max": 1.4767680168151855, |
|
"count": 50 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 6850.6025390625, |
|
"min": 6506.32666015625, |
|
"max": 44799.234375, |
|
"count": 50 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 1499954.0, |
|
"min": 29952.0, |
|
"max": 1499954.0, |
|
"count": 50 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 1499954.0, |
|
"min": 29952.0, |
|
"max": 1499954.0, |
|
"count": 50 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.7591997385025024, |
|
"min": -0.09024693071842194, |
|
"max": 0.8455371260643005, |
|
"count": 50 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 223.96392822265625, |
|
"min": -21.749509811401367, |
|
"max": 255.35220336914062, |
|
"count": 50 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.008865242823958397, |
|
"min": -0.02873266115784645, |
|
"max": 0.3080531358718872, |
|
"count": 50 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -2.615246534347534, |
|
"min": -8.648530960083008, |
|
"max": 74.54885864257812, |
|
"count": 50 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06793310851759575, |
|
"min": 0.06452820453096113, |
|
"max": 0.07404865741028473, |
|
"count": 50 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.0189966277639362, |
|
"min": 0.5163264672379625, |
|
"max": 1.0879468544929598, |
|
"count": 50 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.0154858152212779, |
|
"min": 0.0010252828612129648, |
|
"max": 0.01679059245465656, |
|
"count": 50 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.2322872283191685, |
|
"min": 0.011278111473342614, |
|
"max": 0.24845581312889836, |
|
"count": 50 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 3.0318189894266692e-06, |
|
"min": 3.0318189894266692e-06, |
|
"max": 0.00029676708679192377, |
|
"count": 50 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 4.547728484140004e-05, |
|
"min": 4.547728484140004e-05, |
|
"max": 0.0037379627540124662, |
|
"count": 50 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10101057333333334, |
|
"min": 0.10101057333333334, |
|
"max": 0.19892236190476195, |
|
"count": 50 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5151586000000001, |
|
"min": 1.3924565333333336, |
|
"max": 2.6851005999999993, |
|
"count": 50 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00011095627600000009, |
|
"min": 0.00011095627600000009, |
|
"max": 0.009892343954285714, |
|
"count": 50 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0016643441400000013, |
|
"min": 0.0016643441400000013, |
|
"max": 0.12461415458, |
|
"count": 50 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.009609147906303406, |
|
"min": 0.00955205224454403, |
|
"max": 0.4677009880542755, |
|
"count": 50 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.1441372185945511, |
|
"min": 0.1337287276983261, |
|
"max": 3.273906946182251, |
|
"count": 50 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 249.18260869565216, |
|
"min": 214.65185185185186, |
|
"max": 999.0, |
|
"count": 50 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 28656.0, |
|
"min": 15984.0, |
|
"max": 33117.0, |
|
"count": 50 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.7508173800033071, |
|
"min": -1.0000000521540642, |
|
"max": 1.7695073414703502, |
|
"count": 50 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 201.34399870038033, |
|
"min": -30.431401625275612, |
|
"max": 240.65299843996763, |
|
"count": 50 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.7508173800033071, |
|
"min": -1.0000000521540642, |
|
"max": 1.7695073414703502, |
|
"count": 50 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 201.34399870038033, |
|
"min": -30.431401625275612, |
|
"max": 240.65299843996763, |
|
"count": 50 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.024860629309272474, |
|
"min": 0.021765826649618035, |
|
"max": 9.167079098522663, |
|
"count": 50 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.8589723705663346, |
|
"min": 2.8589723705663346, |
|
"max": 146.6732655763626, |
|
"count": 50 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 50 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 50 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1675156895", |
|
"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=PyramidsTraining --no-graphics --force", |
|
"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": "1675160244" |
|
}, |
|
"total": 3348.9445013249997, |
|
"count": 1, |
|
"self": 0.6063211089995093, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.10440959299990027, |
|
"count": 1, |
|
"self": 0.10440959299990027 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 3348.233770623, |
|
"count": 1, |
|
"self": 1.8131566389415639, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 9.648885517999929, |
|
"count": 1, |
|
"self": 9.648885517999929 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 3336.6922771120585, |
|
"count": 96863, |
|
"self": 1.823896124987641, |
|
"children": { |
|
"env_step": { |
|
"total": 2354.7771621200172, |
|
"count": 96863, |
|
"self": 2202.6545989829756, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 151.0003262889901, |
|
"count": 96863, |
|
"self": 6.311212082003635, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 144.68911420698646, |
|
"count": 93803, |
|
"self": 49.05537672796231, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 95.63373747902415, |
|
"count": 93803, |
|
"self": 95.63373747902415 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 1.1222368480516707, |
|
"count": 96863, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 3342.8342841250465, |
|
"count": 96863, |
|
"is_parallel": true, |
|
"self": 1284.0578550560417, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0058348789999627115, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0035042839999732678, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0023305949999894437, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0023305949999894437 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05924704599999586, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005264979999992647, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00047404199995071394, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00047404199995071394 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.056667810000021746, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.056667810000021746 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.001578696000024138, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004283009999426213, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011503950000815166, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011503950000815166 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 2058.7764290690047, |
|
"count": 96862, |
|
"is_parallel": true, |
|
"self": 41.92970633915911, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 33.25340688794404, |
|
"count": 96862, |
|
"is_parallel": true, |
|
"self": 33.25340688794404 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1846.8967126109562, |
|
"count": 96862, |
|
"is_parallel": true, |
|
"self": 1846.8967126109562 |
|
}, |
|
"steps_from_proto": { |
|
"total": 136.69660323094524, |
|
"count": 96862, |
|
"is_parallel": true, |
|
"self": 31.953351178821663, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 104.74325205212358, |
|
"count": 774896, |
|
"is_parallel": true, |
|
"self": 104.74325205212358 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 980.0912188670536, |
|
"count": 96863, |
|
"self": 3.617603487034785, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 215.61931750301562, |
|
"count": 96863, |
|
"self": 215.35682968901563, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.26248781399999643, |
|
"count": 3, |
|
"self": 0.26248781399999643 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 760.8542978770032, |
|
"count": 691, |
|
"self": 286.62884187999805, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 474.22545599700516, |
|
"count": 34236, |
|
"self": 474.22545599700516 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.749998414714355e-07, |
|
"count": 1, |
|
"self": 8.749998414714355e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.07945047900011559, |
|
"count": 1, |
|
"self": 0.001355904999854829, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.07809457400026076, |
|
"count": 1, |
|
"self": 0.07809457400026076 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |