{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4251229763031006, "min": 0.4212987720966339, "max": 1.4283965826034546, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12733.283203125, "min": 12702.927734375, "max": 43331.83984375, "count": 33 }, "Pyramids.Step.mean": { "value": 989936.0, "min": 29888.0, "max": 989936.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989936.0, "min": 29888.0, "max": 989936.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4152663052082062, "min": -0.08193006366491318, "max": 0.5537070631980896, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 112.12190246582031, "min": -19.827075958251953, "max": 151.1620330810547, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0029726787470281124, "min": -0.01859591342508793, "max": 0.29031625390052795, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.8026232719421387, "min": -4.8535332679748535, "max": 69.96621704101562, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06661175642059082, "min": 0.06571279099064845, "max": 0.07579420192396624, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9991763463088622, "min": 0.6063536153917299, "max": 1.047857467434369, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013982876283504692, "min": 0.0010427224205250226, "max": 0.01476541362602247, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20974314425257037, "min": 0.010427224205250227, "max": 0.20974314425257037, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.423997525366667e-06, "min": 7.423997525366667e-06, "max": 0.0002948472017176, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001113599628805, "min": 0.0001113599628805, "max": 0.0034916866361044997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247463333333333, "min": 0.10247463333333333, "max": 0.19828239999999997, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5371195, "min": 1.4778427, "max": 2.5277988000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025721587000000003, "min": 0.00025721587000000003, "max": 0.00982841176, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00385823805, "min": 0.00385823805, "max": 0.11640316045, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012126035057008266, "min": 0.011980419047176838, "max": 0.5086643695831299, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18189053237438202, "min": 0.16772586107254028, "max": 4.069314956665039, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 435.7142857142857, "min": 370.5903614457831, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30500.0, "min": 16303.0, "max": 33076.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4213856955724102, "min": -0.9999500517733395, "max": 1.5605190251732157, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 99.49699869006872, "min": -31.998401656746864, "max": 131.0835981145501, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4213856955724102, "min": -0.9999500517733395, "max": 1.5605190251732157, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 99.49699869006872, "min": -31.998401656746864, "max": 131.0835981145501, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05461933662275312, "min": 0.047939407969395345, "max": 10.057028827421805, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8233535635927183, "min": 3.581199971784372, "max": 170.9694900661707, "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": "1738821826", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1738824213" }, "total": 2387.00784104, "count": 1, "self": 0.6288574619993597, "children": { "run_training.setup": { "total": 0.019915855000135707, "count": 1, "self": 0.019915855000135707 }, "TrainerController.start_learning": { "total": 2386.3590677230004, "count": 1, "self": 1.5652479169643811, "children": { "TrainerController._reset_env": { "total": 2.36656911099999, "count": 1, "self": 2.36656911099999 }, "TrainerController.advance": { "total": 2382.3287705000357, "count": 63684, "self": 1.5806432520912495, "children": { "env_step": { "total": 1634.9070544889987, "count": 63684, "self": 1465.4703608920167, "children": { "SubprocessEnvManager._take_step": { "total": 168.5220572000685, "count": 63684, "self": 5.076025641085607, "children": { "TorchPolicy.evaluate": { "total": 163.4460315589829, "count": 62541, "self": 163.4460315589829 } } }, "workers": { "total": 0.9146363969134654, "count": 63684, "self": 0.0, "children": { "worker_root": { "total": 2380.676942173904, "count": 63684, "is_parallel": true, "self": 1039.8478337169254, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022113499999250052, "count": 1, "is_parallel": true, "self": 0.0007019060003585764, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015094439995664288, "count": 8, "is_parallel": true, "self": 0.0015094439995664288 } } }, "UnityEnvironment.step": { "total": 0.052378244000010454, "count": 1, "is_parallel": true, "self": 0.0005259299998670031, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000618569000153002, "count": 1, "is_parallel": true, "self": 0.000618569000153002 }, "communicator.exchange": { "total": 0.04952347700009341, "count": 1, "is_parallel": true, "self": 0.04952347700009341 }, "steps_from_proto": { "total": 0.0017102679998970416, "count": 1, "is_parallel": true, "self": 0.0003784660000292206, "children": { "_process_rank_one_or_two_observation": { "total": 0.001331801999867821, "count": 8, "is_parallel": true, "self": 0.001331801999867821 } } } } } } }, "UnityEnvironment.step": { "total": 1340.8291084569787, "count": 63683, "is_parallel": true, "self": 34.2948741400553, "children": { "UnityEnvironment._generate_step_input": { "total": 24.549844133970282, "count": 63683, "is_parallel": true, "self": 24.549844133970282 }, "communicator.exchange": { "total": 1178.6418751799536, "count": 63683, "is_parallel": true, "self": 1178.6418751799536 }, "steps_from_proto": { "total": 103.34251500299956, "count": 63683, "is_parallel": true, "self": 21.282767195044926, "children": { "_process_rank_one_or_two_observation": { "total": 82.05974780795464, "count": 509464, "is_parallel": true, "self": 82.05974780795464 } } } } } } } } } } }, "trainer_advance": { "total": 745.841072758946, "count": 63684, "self": 2.9820099889536777, "children": { "process_trajectory": { "total": 137.5181512889926, "count": 63684, "self": 137.3023540579925, "children": { "RLTrainer._checkpoint": { "total": 0.21579723100012416, "count": 2, "self": 0.21579723100012416 } } }, "_update_policy": { "total": 605.3409114809997, "count": 453, "self": 333.40858812795886, "children": { "TorchPPOOptimizer.update": { "total": 271.93232335304083, "count": 22785, "self": 271.93232335304083 } } } } } } }, "trainer_threads": { "total": 1.0560002010606695e-06, "count": 1, "self": 1.0560002010606695e-06 }, "TrainerController._save_models": { "total": 0.09847913900011918, "count": 1, "self": 0.0015750560005471925, "children": { "RLTrainer._checkpoint": { "total": 0.09690408299957198, "count": 1, "self": 0.09690408299957198 } } } } } } }