{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4975283443927765, "min": 0.4975283443927765, "max": 1.2991137504577637, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14894.0087890625, "min": 14894.0087890625, "max": 39409.9140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989985.0, "min": 29912.0, "max": 989985.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989985.0, "min": 29912.0, "max": 989985.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5420145988464355, "min": -0.11566981673240662, "max": 0.5651412606239319, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 149.05401611328125, "min": -27.876426696777344, "max": 157.10926818847656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.022860458120703697, "min": 0.000766294018831104, "max": 0.4262693524360657, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.286625862121582, "min": 0.21302974224090576, "max": 102.73091125488281, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06770213529481768, "min": 0.06504541253789153, "max": 0.07284051940881738, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9478298941274476, "min": 0.5689209912959292, "max": 1.0448687463894935, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01419600067372109, "min": 0.0008847537395227997, "max": 0.014573843319099196, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19874400943209525, "min": 0.012386552353319195, "max": 0.20403380646738875, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.6231403161285695e-06, "min": 7.6231403161285695e-06, "max": 0.0002948495642168125, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010672396442579998, "min": 0.00010672396442579998, "max": 0.0036359368880210996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254101428571429, "min": 0.10254101428571429, "max": 0.19828318749999999, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355742, "min": 1.4355742, "max": 2.6119789000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002638473271428571, "min": 0.0002638473271428571, "max": 0.00982849043125, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036938625799999994, "min": 0.0036938625799999994, "max": 0.12121669211, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0104046780616045, "min": 0.009974411688745022, "max": 0.5190042853355408, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1456654965877533, "min": 0.13964176177978516, "max": 4.152034282684326, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 364.6951219512195, "min": 364.6951219512195, "max": 982.96875, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29905.0, "min": 17222.0, "max": 34012.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5586147866683242, "min": -0.9213813007809222, "max": 1.5591108202934265, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 126.24779772013426, "min": -29.48420162498951, "max": 129.4061980843544, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5586147866683242, "min": -0.9213813007809222, "max": 1.5591108202934265, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 126.24779772013426, "min": -29.48420162498951, "max": 129.4061980843544, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03943226274920708, "min": 0.03877504102309608, "max": 8.74365240169896, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1940132826857734, "min": 2.9698487007408403, "max": 157.38574323058128, "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": "1759391152", "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": "1759393267" }, "total": 2115.5712855130005, "count": 1, "self": 0.48159041600047203, "children": { "run_training.setup": { "total": 0.03177354500007823, "count": 1, "self": 0.03177354500007823 }, "TrainerController.start_learning": { "total": 2115.057921552, "count": 1, "self": 1.2458474860209208, "children": { "TrainerController._reset_env": { "total": 2.4345691999999417, "count": 1, "self": 2.4345691999999417 }, "TrainerController.advance": { "total": 2111.3067392809794, "count": 63733, "self": 1.2951537049289072, "children": { "env_step": { "total": 1462.664596011007, "count": 63733, "self": 1320.5388819470272, "children": { "SubprocessEnvManager._take_step": { "total": 141.37479887597874, "count": 63733, "self": 4.276720814935288, "children": { "TorchPolicy.evaluate": { "total": 137.09807806104345, "count": 62563, "self": 137.09807806104345 } } }, "workers": { "total": 0.750915188001045, "count": 63733, "self": 0.0, "children": { "worker_root": { "total": 2107.9655048419636, "count": 63733, "is_parallel": true, "self": 897.6363680590594, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017894830000386719, "count": 1, "is_parallel": true, "self": 0.0005961380004464445, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011933449995922274, "count": 8, "is_parallel": true, "self": 0.0011933449995922274 } } }, "UnityEnvironment.step": { "total": 0.04716261399994437, "count": 1, "is_parallel": true, "self": 0.0005286629996135161, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043066000012004224, "count": 1, "is_parallel": true, "self": 0.00043066000012004224 }, "communicator.exchange": { "total": 0.044613970000000336, "count": 1, "is_parallel": true, "self": 0.044613970000000336 }, "steps_from_proto": { "total": 0.0015893210002104752, "count": 1, "is_parallel": true, "self": 0.0003324290000819019, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012568920001285733, "count": 8, "is_parallel": true, "self": 0.0012568920001285733 } } } } } } }, "UnityEnvironment.step": { "total": 1210.3291367829042, "count": 63732, "is_parallel": true, "self": 32.047577717861486, "children": { "UnityEnvironment._generate_step_input": { "total": 21.46167734201981, "count": 63732, "is_parallel": true, "self": 21.46167734201981 }, "communicator.exchange": { "total": 1056.7656863310463, "count": 63732, "is_parallel": true, "self": 1056.7656863310463 }, "steps_from_proto": { "total": 100.05419539197669, "count": 63732, "is_parallel": true, "self": 20.510380127873304, "children": { "_process_rank_one_or_two_observation": { "total": 79.54381526410339, "count": 509856, "is_parallel": true, "self": 79.54381526410339 } } } } } } } } } } }, "trainer_advance": { "total": 647.3469895650437, "count": 63733, "self": 2.589846519049388, "children": { "process_trajectory": { "total": 119.08068760299739, "count": 63733, "self": 118.90722420599786, "children": { "RLTrainer._checkpoint": { "total": 0.17346339699952296, "count": 2, "self": 0.17346339699952296 } } }, "_update_policy": { "total": 525.6764554429969, "count": 457, "self": 293.3393867469947, "children": { "TorchPPOOptimizer.update": { "total": 232.33706869600223, "count": 22749, "self": 232.33706869600223 } } } } } } }, "trainer_threads": { "total": 8.079996405285783e-07, "count": 1, "self": 8.079996405285783e-07 }, "TrainerController._save_models": { "total": 0.07076477700002215, "count": 1, "self": 0.0009428380003555503, "children": { "RLTrainer._checkpoint": { "total": 0.0698219389996666, "count": 1, "self": 0.0698219389996666 } } } } } } }