{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6451210975646973, "min": 0.6451210975646973, "max": 1.6069170236587524, "count": 20 }, "Pyramids.Policy.Entropy.sum": { "value": 3014.005859375, "min": 2957.91796875, "max": 9872.8984375, "count": 20 }, "Pyramids.Step.mean": { "value": 99957.0, "min": 4992.0, "max": 99957.0, "count": 20 }, "Pyramids.Step.sum": { "value": 99957.0, "min": 4992.0, "max": 99957.0, "count": 20 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.10700247436761856, "min": -0.11036466807126999, "max": 0.19310301542282104, "count": 20 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -4.280098915100098, "min": -4.524951457977295, "max": 7.531017780303955, "count": 20 }, "Pyramids.Policy.CuriosityValueEstimate.mean": { "value": 0.31208768486976624, "min": -0.11871524900197983, "max": 0.5101918578147888, "count": 20 }, "Pyramids.Policy.CuriosityValueEstimate.sum": { "value": 12.48350715637207, "min": -4.629894733428955, "max": 21.294876098632812, "count": 20 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06758057010979622, "min": 0.060139786034900077, "max": 0.08101109993355028, "count": 20 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.20274171032938865, "min": 0.060139786034900077, "max": 0.20274171032938865, "count": 20 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00029973042170878004, "min": 0.00029973042170878004, "max": 0.014868051817757078, "count": 20 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0008991912651263402, "min": 0.00041016983324844463, "max": 0.016111305192002785, "count": 20 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.109509778100002e-05, "min": 1.109509778100002e-05, "max": 0.000479520004096, "count": 20 }, "Pyramids.Policy.LearningRate.sum": { "value": 3.328529334300006e-05, "min": 3.328529334300006e-05, "max": 0.0007785600442879999, "count": 20 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10221900000000002, "min": 0.10221900000000002, "max": 0.19590400000000005, "count": 20 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.30665700000000007, "min": 0.13778899999999994, "max": 0.38347300000000006, "count": 20 }, "Pyramids.Policy.Beta.mean": { "value": 0.00023167810000000047, "min": 0.00023167810000000047, "max": 0.0095908096, "count": 20 }, "Pyramids.Policy.Beta.sum": { "value": 0.0006950343000000014, "min": 0.0006950343000000014, "max": 0.015575628800000001, "count": 20 }, "Pyramids.Losses.CuriosityForwardLoss.mean": { "value": 0.1331191056088549, "min": 0.13191234056527415, "max": 1.062101550400257, "count": 20 }, "Pyramids.Losses.CuriosityForwardLoss.sum": { "value": 0.3993573168265647, "min": 0.1845689576960379, "max": 1.062101550400257, "count": 20 }, "Pyramids.Losses.CuriosityInverseLoss.mean": { "value": 0.19341666065103527, "min": 0.19341666065103527, "max": 1.0087984967976809, "count": 20 }, "Pyramids.Losses.CuriosityInverseLoss.sum": { "value": 0.5802499819531058, "min": 0.2827631707793923, "max": 1.0708979216093817, "count": 20 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 514.0, "max": 999.0, "count": 10 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 14985.0, "min": 514.0, "max": 15984.0, "count": 10 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -1.0000000521540642, "min": -1.0000000521540642, "max": 1.4860000014305115, "count": 12 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -6.000000312924385, "min": -16.000000834465027, "max": 2.375999867916107, "count": 12 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -1.0000000521540642, "min": -1.0000000521540642, "max": 1.4860000014305115, "count": 12 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -6.000000312924385, "min": -16.000000834465027, "max": 2.375999867916107, "count": 12 }, "Pyramids.Policy.CuriosityReward.mean": { "value": 2.8052185798684754, "min": 2.8052185798684754, "max": 6.720910437405109, "count": 12 }, "Pyramids.Policy.CuriosityReward.sum": { "value": 16.831311479210854, "min": 3.1243360936641693, "max": 107.53456699848175, "count": 12 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1716714195", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Pyramids.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "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": "1716714437" }, "total": 241.32956991600076, "count": 1, "self": 0.5013118150000082, "children": { "run_training.setup": { "total": 0.056518850000429666, "count": 1, "self": 0.056518850000429666 }, "TrainerController.start_learning": { "total": 240.77173925100033, "count": 1, "self": 0.18175960001099156, "children": { "TrainerController._reset_env": { "total": 2.4149710379997487, "count": 1, "self": 2.4149710379997487 }, "TrainerController.advance": { "total": 238.05032934099017, "count": 6304, "self": 0.2095663039754072, "children": { "env_step": { "total": 155.05327726704854, "count": 6304, "self": 136.69235677504003, "children": { "SubprocessEnvManager._take_step": { "total": 18.247605549026957, "count": 6304, "self": 0.5990804590810512, "children": { "TorchPolicy.evaluate": { "total": 17.648525089945906, "count": 6292, "self": 17.648525089945906 } } }, "workers": { "total": 0.11331494298156031, "count": 6304, "self": 0.0, "children": { "worker_root": { "total": 240.0926715700234, "count": 6304, "is_parallel": true, "self": 118.93710902202383, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002296657000442792, "count": 1, "is_parallel": true, "self": 0.0006495540001196787, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016471030003231135, "count": 8, "is_parallel": true, "self": 0.0016471030003231135 } } }, "UnityEnvironment.step": { "total": 0.049303064000014274, "count": 1, "is_parallel": true, "self": 0.0006382899991876911, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000485536999804026, "count": 1, "is_parallel": true, "self": 0.000485536999804026 }, "communicator.exchange": { "total": 0.0463892420002594, "count": 1, "is_parallel": true, "self": 0.0463892420002594 }, "steps_from_proto": { "total": 0.001789995000763156, "count": 1, "is_parallel": true, "self": 0.0003914800026905141, "children": { "_process_rank_one_or_two_observation": { "total": 0.001398514998072642, "count": 8, "is_parallel": true, "self": 0.001398514998072642 } } } } } } }, "UnityEnvironment.step": { "total": 121.15556254799958, "count": 6303, "is_parallel": true, "self": 3.98279508106134, "children": { "UnityEnvironment._generate_step_input": { "total": 2.6460406800015335, "count": 6303, "is_parallel": true, "self": 2.6460406800015335 }, "communicator.exchange": { "total": 103.0294933479372, "count": 6303, "is_parallel": true, "self": 103.0294933479372 }, "steps_from_proto": { "total": 11.497233438999501, "count": 6303, "is_parallel": true, "self": 2.431688196011237, "children": { "_process_rank_one_or_two_observation": { "total": 9.065545242988264, "count": 50424, "is_parallel": true, "self": 9.065545242988264 } } } } } } } } } } }, "trainer_advance": { "total": 82.78748576996622, "count": 6304, "self": 0.25155939395790483, "children": { "process_trajectory": { "total": 12.518190540013165, "count": 6304, "self": 12.518190540013165 }, "_update_policy": { "total": 70.01773583599515, "count": 33, "self": 46.00202858499506, "children": { "TorchPPOOptimizer.update": { "total": 24.015707251000094, "count": 2325, "self": 24.015707251000094 } } } } } } }, "trainer_threads": { "total": 8.669994713272899e-07, "count": 1, "self": 8.669994713272899e-07 }, "TrainerController._save_models": { "total": 0.12467840499994054, "count": 1, "self": 0.0019627969995781314, "children": { "RLTrainer._checkpoint": { "total": 0.12271560800036241, "count": 1, "self": 0.12271560800036241 } } } } } } }