|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.32320356369018555, |
|
"min": 0.32320356369018555, |
|
"max": 1.4934890270233154, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 9639.22265625, |
|
"min": 9639.22265625, |
|
"max": 45306.484375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989890.0, |
|
"min": 29952.0, |
|
"max": 989890.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989890.0, |
|
"min": 29952.0, |
|
"max": 989890.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.656840980052948, |
|
"min": -0.12254790961742401, |
|
"max": 0.656840980052948, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 187.8565216064453, |
|
"min": -29.4114990234375, |
|
"max": 187.8565216064453, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.0140081737190485, |
|
"min": 0.01093398965895176, |
|
"max": 0.1996997445821762, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 4.006337642669678, |
|
"min": 3.0177810192108154, |
|
"max": 48.12763977050781, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06893980426372895, |
|
"min": 0.06446499529660546, |
|
"max": 0.07498371068418618, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9651572596922052, |
|
"min": 0.5248859747893032, |
|
"max": 1.0235142301535234, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.015038418989639642, |
|
"min": 0.0016632156678265434, |
|
"max": 0.01712153538444129, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.210537865854955, |
|
"min": 0.02257767585433619, |
|
"max": 0.24402293046781173, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.768747410449999e-06, |
|
"min": 7.768747410449999e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010876246374629999, |
|
"min": 0.00010876246374629999, |
|
"max": 0.003508375430541599, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10258955000000002, |
|
"min": 0.10258955000000002, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4362537000000002, |
|
"min": 1.3886848, |
|
"max": 2.5694584000000003, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00026869604500000005, |
|
"min": 0.00026869604500000005, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003761744630000001, |
|
"min": 0.003761744630000001, |
|
"max": 0.11696889415999999, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.013765105046331882, |
|
"min": 0.013765105046331882, |
|
"max": 0.3739595115184784, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.1927114725112915, |
|
"min": 0.1927114725112915, |
|
"max": 2.6177165508270264, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 286.16190476190474, |
|
"min": 286.16190476190474, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30047.0, |
|
"min": 15984.0, |
|
"max": 33042.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.6947847479865665, |
|
"min": -1.0000000521540642, |
|
"max": 1.6947847479865665, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 177.95239853858948, |
|
"min": -29.45660163462162, |
|
"max": 177.95239853858948, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.6947847479865665, |
|
"min": -1.0000000521540642, |
|
"max": 1.6947847479865665, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 177.95239853858948, |
|
"min": -29.45660163462162, |
|
"max": 177.95239853858948, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.040237358018168294, |
|
"min": 0.040237358018168294, |
|
"max": 7.65089419670403, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 4.224922591907671, |
|
"min": 4.224922591907671, |
|
"max": 122.41430714726448, |
|
"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": "1678239200", |
|
"python_version": "3.8.10 (default, Jun 22 2022, 20:18:18) \n[GCC 9.4.0]", |
|
"command_line_arguments": "/home/hanbk/torch_venv/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": "1.8.2+cu111", |
|
"numpy_version": "1.20.1", |
|
"end_time_seconds": "1678240685" |
|
}, |
|
"total": 1485.2815037129913, |
|
"count": 1, |
|
"self": 0.2696852450608276, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.17986562696751207, |
|
"count": 1, |
|
"self": 0.17986562696751207 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1484.831952840963, |
|
"count": 1, |
|
"self": 1.3780222524655983, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 4.125219576002564, |
|
"count": 1, |
|
"self": 4.125219576002564 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1479.245007778518, |
|
"count": 63988, |
|
"self": 1.300217540934682, |
|
"children": { |
|
"env_step": { |
|
"total": 856.6199052805896, |
|
"count": 63988, |
|
"self": 734.4650882972637, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 121.31774410011712, |
|
"count": 63988, |
|
"self": 3.758611876575742, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 117.55913222354138, |
|
"count": 62558, |
|
"self": 42.255259597324766, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 75.30387262621662, |
|
"count": 62558, |
|
"self": 75.30387262621662 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.837072883208748, |
|
"count": 63988, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1482.9807859479333, |
|
"count": 63988, |
|
"is_parallel": true, |
|
"self": 828.4839641454746, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0015014269738458097, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005025019636377692, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0009989250102080405, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0009989250102080405 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.026054731977637857, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0002761069335974753, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0002606900525279343, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0002606900525279343 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.02455824101343751, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.02455824101343751 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0009596939780749381, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00027872587088495493, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0006809681071899831, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0006809681071899831 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 654.4968218024587, |
|
"count": 63987, |
|
"is_parallel": true, |
|
"self": 17.056305111385882, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 12.360483438300434, |
|
"count": 63987, |
|
"is_parallel": true, |
|
"self": 12.360483438300434 |
|
}, |
|
"communicator.exchange": { |
|
"total": 568.7441661244957, |
|
"count": 63987, |
|
"is_parallel": true, |
|
"self": 568.7441661244957 |
|
}, |
|
"steps_from_proto": { |
|
"total": 56.33586712827673, |
|
"count": 63987, |
|
"is_parallel": true, |
|
"self": 15.751355388842057, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 40.584511739434674, |
|
"count": 511896, |
|
"is_parallel": true, |
|
"self": 40.584511739434674 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 621.3248849569936, |
|
"count": 63988, |
|
"self": 2.416245396307204, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 125.43734488834161, |
|
"count": 63988, |
|
"self": 125.26885112922173, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.16849375911988318, |
|
"count": 2, |
|
"self": 0.16849375911988318 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 493.4712946723448, |
|
"count": 453, |
|
"self": 173.18949163646903, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 320.2818030358758, |
|
"count": 22791, |
|
"self": 320.2818030358758 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.689239621162415e-07, |
|
"count": 1, |
|
"self": 8.689239621162415e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08370236505288631, |
|
"count": 1, |
|
"self": 0.001002102973870933, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.08270026207901537, |
|
"count": 1, |
|
"self": 0.08270026207901537 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |