{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.37979206442832947, "min": 0.3720703721046448, "max": 1.4881356954574585, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11351.2255859375, "min": 11191.876953125, "max": 45144.0859375, "count": 33 }, "Pyramids.Step.mean": { "value": 989876.0, "min": 29952.0, "max": 989876.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989876.0, "min": 29952.0, "max": 989876.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5227780938148499, "min": -0.12358661741018295, "max": 0.6054206490516663, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 142.19564819335938, "min": -29.784374237060547, "max": 172.54489135742188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.03182263299822807, "min": -0.03182263299822807, "max": 0.31523266434669495, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -8.655755996704102, "min": -8.92076587677002, "max": 75.65583801269531, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06809575499695104, "min": 0.06441670647453275, "max": 0.07387717720546472, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9533405699573146, "min": 0.4921643173488676, "max": 1.0326838654582389, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015499743084850099, "min": 0.0005963593982828933, "max": 0.016060830902590948, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2169964031879014, "min": 0.00826083271974427, "max": 0.22485163263627328, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.76388312635714e-06, "min": 7.76388312635714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010869436376899995, "min": 0.00010869436376899995, "max": 0.003255786514737899, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258792857142858, "min": 0.10258792857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.436231, "min": 1.3691136000000002, "max": 2.4016118000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026853406428571414, "min": 0.00026853406428571414, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003759476899999998, "min": 0.003759476899999998, "max": 0.10854768379000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013619273900985718, "min": 0.013440021313726902, "max": 0.49954405426979065, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19066983461380005, "min": 0.18816030025482178, "max": 3.4968082904815674, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 336.90909090909093, "min": 316.80434782608694, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29648.0, "min": 15984.0, "max": 33053.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5461864957816145, "min": -1.0000000521540642, "max": 1.6614543290241905, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 137.6105981245637, "min": -32.000001668930054, "max": 152.85379827022552, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5461864957816145, "min": -1.0000000521540642, "max": 1.6614543290241905, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 137.6105981245637, "min": -32.000001668930054, "max": 152.85379827022552, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04730108043825086, "min": 0.04730108043825086, "max": 10.12188120931387, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.209796159004327, "min": 4.086894369800575, "max": 161.9500993490219, "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": "1713796042", "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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713799005" }, "total": 2962.808823208, "count": 1, "self": 0.679635672000586, "children": { "run_training.setup": { "total": 0.05847314799984815, "count": 1, "self": 0.05847314799984815 }, "TrainerController.start_learning": { "total": 2962.0707143879995, "count": 1, "self": 2.2944234359624716, "children": { "TrainerController._reset_env": { "total": 2.4587119899999834, "count": 1, "self": 2.4587119899999834 }, "TrainerController.advance": { "total": 2957.213840490037, "count": 63765, "self": 2.3857757940168085, "children": { "env_step": { "total": 2190.946831646018, "count": 63765, "self": 1999.0173396051287, "children": { "SubprocessEnvManager._take_step": { "total": 190.46712072092828, "count": 63765, "self": 6.765093387895149, "children": { "TorchPolicy.evaluate": { "total": 183.70202733303313, "count": 62556, "self": 183.70202733303313 } } }, "workers": { "total": 1.4623713199609938, "count": 63765, "self": 0.0, "children": { "worker_root": { "total": 2954.5092846899956, "count": 63765, "is_parallel": true, "self": 1137.9449793889908, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002613567000025796, "count": 1, "is_parallel": true, "self": 0.0008240169995588076, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017895500004669884, "count": 8, "is_parallel": true, "self": 0.0017895500004669884 } } }, "UnityEnvironment.step": { "total": 0.11501726999995299, "count": 1, "is_parallel": true, "self": 0.0008606319997852552, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048315200001525227, "count": 1, "is_parallel": true, "self": 0.00048315200001525227 }, "communicator.exchange": { "total": 0.10627658600014911, "count": 1, "is_parallel": true, "self": 0.10627658600014911 }, "steps_from_proto": { "total": 0.00739690000000337, "count": 1, "is_parallel": true, "self": 0.0004865739999786456, "children": { "_process_rank_one_or_two_observation": { "total": 0.006910326000024725, "count": 8, "is_parallel": true, "self": 0.006910326000024725 } } } } } } }, "UnityEnvironment.step": { "total": 1816.5643053010049, "count": 63764, "is_parallel": true, "self": 48.84070164083073, "children": { "UnityEnvironment._generate_step_input": { "total": 31.221794234979598, "count": 63764, "is_parallel": true, "self": 31.221794234979598 }, "communicator.exchange": { "total": 1600.1692816560505, "count": 63764, "is_parallel": true, "self": 1600.1692816560505 }, "steps_from_proto": { "total": 136.332527769144, "count": 63764, "is_parallel": true, "self": 29.108274179460977, "children": { "_process_rank_one_or_two_observation": { "total": 107.22425358968303, "count": 510112, "is_parallel": true, "self": 107.22425358968303 } } } } } } } } } } }, "trainer_advance": { "total": 763.8812330500023, "count": 63765, "self": 4.267438620002849, "children": { "process_trajectory": { "total": 159.36280390800016, "count": 63765, "self": 159.1029315610001, "children": { "RLTrainer._checkpoint": { "total": 0.259872347000055, "count": 2, "self": 0.259872347000055 } } }, "_update_policy": { "total": 600.2509905219993, "count": 444, "self": 349.20672285895876, "children": { "TorchPPOOptimizer.update": { "total": 251.0442676630405, "count": 22806, "self": 251.0442676630405 } } } } } } }, "trainer_threads": { "total": 1.2890004654764198e-06, "count": 1, "self": 1.2890004654764198e-06 }, "TrainerController._save_models": { "total": 0.10373718299979373, "count": 1, "self": 0.0017343110002911999, "children": { "RLTrainer._checkpoint": { "total": 0.10200287199950253, "count": 1, "self": 0.10200287199950253 } } } } } } }