|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.43280908465385437, |
|
"min": 0.42923521995544434, |
|
"max": 1.500061273574829, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 13039.671875, |
|
"min": 12856.453125, |
|
"max": 45505.859375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989954.0, |
|
"min": 29952.0, |
|
"max": 989954.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989954.0, |
|
"min": 29952.0, |
|
"max": 989954.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.08247698098421097, |
|
"min": -0.10695645213127136, |
|
"max": -0.06300479918718338, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -19.876953125, |
|
"min": -25.348678588867188, |
|
"max": -15.18415641784668, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.CuriosityValueEstimate.mean": { |
|
"value": 0.1753985434770584, |
|
"min": 0.1753985434770584, |
|
"max": 0.5252812504768372, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.CuriosityValueEstimate.sum": { |
|
"value": 42.27104949951172, |
|
"min": 42.27104949951172, |
|
"max": 127.11805725097656, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06790589252926237, |
|
"min": 0.06468099005827435, |
|
"max": 0.07428065941530597, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9506824954096731, |
|
"min": 0.4965578865113698, |
|
"max": 0.9834449033389467, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.0009964273950411398, |
|
"min": 8.107707583812088e-05, |
|
"max": 0.004561436653644684, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.013949983530575957, |
|
"min": 0.0010540019858955715, |
|
"max": 0.03193005657551279, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.789211689342853e-06, |
|
"min": 7.789211689342853e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010904896365079993, |
|
"min": 0.00010904896365079993, |
|
"max": 0.0033319242893585996, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10259637142857143, |
|
"min": 0.10259637142857143, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4363492, |
|
"min": 1.3886848, |
|
"max": 2.3864619, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002693775057142856, |
|
"min": 0.0002693775057142856, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003771285079999999, |
|
"min": 0.003771285079999999, |
|
"max": 0.11107307585999998, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.CuriosityForwardLoss.mean": { |
|
"value": 0.08162781434800183, |
|
"min": 0.08162781434800183, |
|
"max": 0.4629778496352176, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.CuriosityForwardLoss.sum": { |
|
"value": 1.1427894008720256, |
|
"min": 1.1427894008720256, |
|
"max": 3.240844947446523, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.CuriosityInverseLoss.mean": { |
|
"value": 0.06705228008366718, |
|
"min": 0.06705228008366718, |
|
"max": 0.7394397138650047, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.CuriosityInverseLoss.sum": { |
|
"value": 0.9387319211713404, |
|
"min": 0.9387319211713404, |
|
"max": 5.1760779970550335, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 982.8333333333334, |
|
"min": 946.8846153846154, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29485.0, |
|
"min": 15984.0, |
|
"max": 33054.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": -0.8500667169690133, |
|
"min": -1.0000000521540642, |
|
"max": -0.6973871406047575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": -25.502001509070396, |
|
"min": -31.997201651334763, |
|
"max": -16.000000834465027, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": -0.8500667169690133, |
|
"min": -1.0000000521540642, |
|
"max": -0.6973871406047575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": -25.502001509070396, |
|
"min": -31.997201651334763, |
|
"max": -16.000000834465027, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.CuriosityReward.mean": { |
|
"value": 1.6790156602859496, |
|
"min": 1.6790156602859496, |
|
"max": 6.546968856826425, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.CuriosityReward.sum": { |
|
"value": 50.37046980857849, |
|
"min": 49.88315750658512, |
|
"max": 194.03472942113876, |
|
"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": "1720715578", |
|
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/Pyramids.yaml --env=/content/training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining3 --no-graphics", |
|
"mlagents_version": "1.1.0.dev0", |
|
"mlagents_envs_version": "1.1.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "2.3.0+cu121", |
|
"numpy_version": "1.23.5", |
|
"end_time_seconds": "1720717816" |
|
}, |
|
"total": 2237.303348728, |
|
"count": 1, |
|
"self": 0.48266690200034645, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.06598124999982247, |
|
"count": 1, |
|
"self": 0.06598124999982247 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2236.754700576, |
|
"count": 1, |
|
"self": 1.3786383029200806, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 2.522124203000203, |
|
"count": 1, |
|
"self": 2.522124203000203 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2232.7662233370793, |
|
"count": 62957, |
|
"self": 1.4477401920994453, |
|
"children": { |
|
"env_step": { |
|
"total": 1466.8395696330526, |
|
"count": 62957, |
|
"self": 1328.9225865030285, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 137.0742994699849, |
|
"count": 62957, |
|
"self": 4.673299340139238, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 132.40100012984567, |
|
"count": 62562, |
|
"self": 132.40100012984567 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.8426836600392562, |
|
"count": 62957, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2231.75681254583, |
|
"count": 62957, |
|
"is_parallel": true, |
|
"self": 1025.0121161818224, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0020646590000978904, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006320830007098266, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0014325759993880638, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0014325759993880638 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05041338299997733, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006721239997204975, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005186770004002028, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005186770004002028 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04748523899979773, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04748523899979773 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0017373430000588996, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003552759999365662, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013820670001223334, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013820670001223334 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1206.7446963640077, |
|
"count": 62956, |
|
"is_parallel": true, |
|
"self": 34.22382334201575, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 23.81617521398948, |
|
"count": 62956, |
|
"is_parallel": true, |
|
"self": 23.81617521398948 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1050.4539883309963, |
|
"count": 62956, |
|
"is_parallel": true, |
|
"self": 1050.4539883309963 |
|
}, |
|
"steps_from_proto": { |
|
"total": 98.25070947700624, |
|
"count": 62956, |
|
"is_parallel": true, |
|
"self": 19.902090627814687, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 78.34861884919155, |
|
"count": 503648, |
|
"is_parallel": true, |
|
"self": 78.34861884919155 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 764.4789135119272, |
|
"count": 62957, |
|
"self": 2.327242099826435, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 122.59124763509317, |
|
"count": 62957, |
|
"self": 122.34434010809218, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.24690752700098528, |
|
"count": 2, |
|
"self": 0.24690752700098528 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 639.5604237770076, |
|
"count": 432, |
|
"self": 426.4940858090349, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 213.0663379679727, |
|
"count": 22872, |
|
"self": 213.0663379679727 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0769999789772555e-06, |
|
"count": 1, |
|
"self": 1.0769999789772555e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08771365600023273, |
|
"count": 1, |
|
"self": 0.001269917000172427, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.0864437390000603, |
|
"count": 1, |
|
"self": 0.0864437390000603 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |