|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.7770655751228333, |
|
"min": 0.7149478793144226, |
|
"max": 1.406144380569458, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 23113.0390625, |
|
"min": 21459.875, |
|
"max": 42656.796875, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 479909.0, |
|
"min": 29952.0, |
|
"max": 479909.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 479909.0, |
|
"min": 29952.0, |
|
"max": 479909.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.03145706281065941, |
|
"min": -0.08600706607103348, |
|
"max": 0.03145706281065941, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 7.706980228424072, |
|
"min": -20.813709259033203, |
|
"max": 7.706980228424072, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.023792993277311325, |
|
"min": 0.02291889861226082, |
|
"max": 0.36386147141456604, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 5.829283237457275, |
|
"min": 5.54637336730957, |
|
"max": 86.23516845703125, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06791810940027286, |
|
"min": 0.061117838686500225, |
|
"max": 0.07237898667573833, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9508535316038201, |
|
"min": 0.49955658265891295, |
|
"max": 1.0073865971655187, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.005673865730417323, |
|
"min": 0.0012421922685924797, |
|
"max": 0.006936883556637352, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.07943412022584252, |
|
"min": 0.013664114954517276, |
|
"max": 0.07943412022584252, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 2.1245021489785714e-05, |
|
"min": 2.1245021489785714e-05, |
|
"max": 0.00029030126037577137, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.000297430300857, |
|
"min": 0.000297430300857, |
|
"max": 0.0028545069484978, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10708164285714285, |
|
"min": 0.10708164285714285, |
|
"max": 0.19676708571428575, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.499143, |
|
"min": 1.3773696000000002, |
|
"max": 2.3390538, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0007174561214285717, |
|
"min": 0.0007174561214285717, |
|
"max": 0.00967703186285714, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.010044385700000004, |
|
"min": 0.010044385700000004, |
|
"max": 0.09518506978, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.021279560402035713, |
|
"min": 0.021279560402035713, |
|
"max": 0.4321460425853729, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.2979138493537903, |
|
"min": 0.2979138493537903, |
|
"max": 3.025022268295288, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 794.2432432432432, |
|
"min": 794.2432432432432, |
|
"max": 999.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29387.0, |
|
"min": 15984.0, |
|
"max": 32544.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": -0.010578988610129608, |
|
"min": -1.0000000521540642, |
|
"max": -0.010578988610129608, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": -0.4020015671849251, |
|
"min": -30.576001703739166, |
|
"max": -0.4020015671849251, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": -0.010578988610129608, |
|
"min": -1.0000000521540642, |
|
"max": -0.010578988610129608, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": -0.4020015671849251, |
|
"min": -30.576001703739166, |
|
"max": -0.4020015671849251, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.17755138295040906, |
|
"min": 0.17755138295040906, |
|
"max": 8.079890253022313, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 6.746952552115545, |
|
"min": 6.746952552115545, |
|
"max": 129.278244048357, |
|
"count": 16 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 16 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1667244327", |
|
"python_version": "3.7.15 (default, Oct 12 2022, 19:14:55) \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": "1667245340" |
|
}, |
|
"total": 1012.2812821070002, |
|
"count": 1, |
|
"self": 0.44302224300008675, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.04361447399998042, |
|
"count": 1, |
|
"self": 0.04361447399998042 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1011.79464539, |
|
"count": 1, |
|
"self": 0.6574091919956118, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 8.211406742999998, |
|
"count": 1, |
|
"self": 8.211406742999998 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1002.8339853440046, |
|
"count": 31595, |
|
"self": 0.7089514950024522, |
|
"children": { |
|
"env_step": { |
|
"total": 652.6859832749982, |
|
"count": 31595, |
|
"self": 599.6982659899926, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 52.63924032100823, |
|
"count": 31595, |
|
"self": 2.255999688999111, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 50.38324063200912, |
|
"count": 31316, |
|
"self": 17.29556965400309, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 33.08767097800603, |
|
"count": 31316, |
|
"self": 33.08767097800603 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.3484769639973706, |
|
"count": 31595, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1009.5508555149788, |
|
"count": 31595, |
|
"is_parallel": true, |
|
"self": 459.1501037809729, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0063398819999633815, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.004398583999886796, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0019412980000765856, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0019412980000765856 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.046763196999961565, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005013319999420673, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00047640499997214647, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00047640499997214647 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.044228671000041686, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.044228671000041686 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.001556789000005665, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00042796799999678115, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011288210000088839, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011288210000088839 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 550.4007517340059, |
|
"count": 31594, |
|
"is_parallel": true, |
|
"self": 13.836279523024928, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 11.538736471988727, |
|
"count": 31594, |
|
"is_parallel": true, |
|
"self": 11.538736471988727 |
|
}, |
|
"communicator.exchange": { |
|
"total": 471.58952602199383, |
|
"count": 31594, |
|
"is_parallel": true, |
|
"self": 471.58952602199383 |
|
}, |
|
"steps_from_proto": { |
|
"total": 53.43620971699846, |
|
"count": 31594, |
|
"is_parallel": true, |
|
"self": 11.59857812098494, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 41.83763159601352, |
|
"count": 252752, |
|
"is_parallel": true, |
|
"self": 41.83763159601352 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 349.43905057400406, |
|
"count": 31595, |
|
"self": 1.163610428005427, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 78.96369078700042, |
|
"count": 31595, |
|
"self": 78.86017162400032, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.10351916300010089, |
|
"count": 1, |
|
"self": 0.10351916300010089 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 269.3117493589982, |
|
"count": 215, |
|
"self": 105.35115697598968, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 163.96059238300853, |
|
"count": 11412, |
|
"self": 163.96059238300853 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.1449999419710366e-06, |
|
"count": 1, |
|
"self": 1.1449999419710366e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.091842965999831, |
|
"count": 1, |
|
"self": 0.0016183259999706934, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.0902246399998603, |
|
"count": 1, |
|
"self": 0.0902246399998603 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |