{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3604281544685364, "min": 0.35506731271743774, "max": 1.3652037382125854, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10760.943359375, "min": 10690.6689453125, "max": 41414.8203125, "count": 33 }, "Pyramids.Step.mean": { "value": 989972.0, "min": 29952.0, "max": 989972.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989972.0, "min": 29952.0, "max": 989972.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6344459652900696, "min": -0.08143594861030579, "max": 0.683842658996582, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 182.08599853515625, "min": -19.62606430053711, "max": 197.9730682373047, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.006639602594077587, "min": -0.00932199228554964, "max": 0.5745494365692139, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.9055659770965576, "min": -2.7033777236938477, "max": 136.168212890625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06701613959578229, "min": 0.06477685024116758, "max": 0.07397381106940364, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0052420939367344, "min": 0.5044700328779845, "max": 1.1016671022539501, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01677165952601677, "min": 0.000265572416849074, "max": 0.01677165952601677, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.25157489289025153, "min": 0.0034524414190379616, "max": 0.25157489289025153, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.545497484866665e-06, "min": 7.545497484866665e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011318246227299998, "min": 0.00011318246227299998, "max": 0.003508375130541699, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251513333333336, "min": 0.10251513333333336, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5377270000000003, "min": 1.3886848, "max": 2.5724949000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026126181999999997, "min": 0.00026126181999999997, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039189273, "min": 0.0039189273, "max": 0.11696888417, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011511927470564842, "min": 0.011511927470564842, "max": 0.5825320482254028, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17267891764640808, "min": 0.1636643409729004, "max": 4.077724456787109, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 294.2718446601942, "min": 284.48571428571427, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30310.0, "min": 15984.0, "max": 33552.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.69250290182609, "min": -1.0000000521540642, "max": 1.69250290182609, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 174.32779888808727, "min": -30.412801668047905, "max": 176.8181977123022, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.69250290182609, "min": -1.0000000521540642, "max": 1.69250290182609, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 174.32779888808727, "min": -30.412801668047905, "max": 176.8181977123022, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03463746619010494, "min": 0.034246506050389834, "max": 12.726239141076803, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.5676590175808087, "min": 3.5676590175808087, "max": 203.61982625722885, "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": "1772201830", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1772204363" }, "total": 2533.417895585, "count": 1, "self": 0.4765445760003786, "children": { "run_training.setup": { "total": 0.02320981100001518, "count": 1, "self": 0.02320981100001518 }, "TrainerController.start_learning": { "total": 2532.918141198, "count": 1, "self": 1.6995406228716092, "children": { "TrainerController._reset_env": { "total": 2.2266405200002737, "count": 1, "self": 2.2266405200002737 }, "TrainerController.advance": { "total": 2528.9064843501287, "count": 64180, "self": 1.7568639410874312, "children": { "env_step": { "total": 1832.0136413650039, "count": 64180, "self": 1658.006302359966, "children": { "SubprocessEnvManager._take_step": { "total": 173.0047364910556, "count": 64180, "self": 5.144711034152806, "children": { "TorchPolicy.evaluate": { "total": 167.8600254569028, "count": 62552, "self": 167.8600254569028 } } }, "workers": { "total": 1.0026025139823105, "count": 64180, "self": 0.0, "children": { "worker_root": { "total": 2525.526496044095, "count": 64180, "is_parallel": true, "self": 1000.0451453080323, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017015050002555654, "count": 1, "is_parallel": true, "self": 0.0005535790005524177, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011479259997031477, "count": 8, "is_parallel": true, "self": 0.0011479259997031477 } } }, "UnityEnvironment.step": { "total": 0.047545370999614534, "count": 1, "is_parallel": true, "self": 0.0005856800003130047, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045096799976818147, "count": 1, "is_parallel": true, "self": 0.00045096799976818147 }, "communicator.exchange": { "total": 0.04487906899976224, "count": 1, "is_parallel": true, "self": 0.04487906899976224 }, "steps_from_proto": { "total": 0.001629653999771108, "count": 1, "is_parallel": true, "self": 0.0003286799997113121, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013009740000597958, "count": 8, "is_parallel": true, "self": 0.0013009740000597958 } } } } } } }, "UnityEnvironment.step": { "total": 1525.4813507360627, "count": 64179, "is_parallel": true, "self": 36.97438997812105, "children": { "UnityEnvironment._generate_step_input": { "total": 24.329459816044164, "count": 64179, "is_parallel": true, "self": 24.329459816044164 }, "communicator.exchange": { "total": 1349.7770538788764, "count": 64179, "is_parallel": true, "self": 1349.7770538788764 }, "steps_from_proto": { "total": 114.40044706302115, "count": 64179, "is_parallel": true, "self": 24.65027404372404, "children": { "_process_rank_one_or_two_observation": { "total": 89.75017301929711, "count": 513432, "is_parallel": true, "self": 89.75017301929711 } } } } } } } } } } }, "trainer_advance": { "total": 695.1359790440374, "count": 64180, "self": 3.3073379071229283, "children": { "process_trajectory": { "total": 131.23861532890896, "count": 64180, "self": 131.05917522790878, "children": { "RLTrainer._checkpoint": { "total": 0.17944010100018204, "count": 2, "self": 0.17944010100018204 } } }, "_update_policy": { "total": 560.5900258080055, "count": 452, "self": 308.3852236099806, "children": { "TorchPPOOptimizer.update": { "total": 252.20480219802494, "count": 22767, "self": 252.20480219802494 } } } } } } }, "trainer_threads": { "total": 1.0059993655886501e-06, "count": 1, "self": 1.0059993655886501e-06 }, "TrainerController._save_models": { "total": 0.08547469899986027, "count": 1, "self": 0.0010729289997470914, "children": { "RLTrainer._checkpoint": { "total": 0.08440177000011317, "count": 1, "self": 0.08440177000011317 } } } } } } }