{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.38860538601875305, "min": 0.3785582482814789, "max": 1.5276380777359009, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11645.7265625, "min": 11284.064453125, "max": 46342.4296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989955.0, "min": 29952.0, "max": 989955.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989955.0, "min": 29952.0, "max": 989955.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6482967138290405, "min": -0.10192558914422989, "max": 0.6482967138290405, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 182.81967163085938, "min": -24.564067840576172, "max": 182.81967163085938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.05729641392827034, "min": 0.05729641392827034, "max": 0.9635476469993591, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 16.157588958740234, "min": 16.157588958740234, "max": 232.21498107910156, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.033001030373963576, "min": 0.029435515058659285, "max": 0.0378014595504889, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.231007212617745, "min": 0.14908568704420833, "max": 0.3024116764039112, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016108828508073374, "min": 0.0011180835341032694, "max": 0.18189138451219544, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.11276179955651362, "min": 0.007826584738722886, "max": 0.7275655380487818, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.993766876398572e-05, "min": 7.993766876398572e-05, "max": 0.0029544960015168, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0005595636813479001, "min": 0.0005595636813479001, "max": 0.0194365050521165, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10266458571428572, "min": 0.10266458571428572, "max": 0.19848320000000003, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.7186521, "min": 0.7186521, "max": 1.3957381, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000276192112857143, "min": 0.000276192112857143, "max": 0.009848471680000002, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0019333447900000008, "min": 0.0019333447900000008, "max": 0.06479356165, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.03974464535713196, "min": 0.03974464535713196, "max": 1.2891017198562622, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2782125174999237, "min": 0.2782125174999237, "max": 5.156406879425049, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 290.5098039215686, "min": 290.5098039215686, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29632.0, "min": 15984.0, "max": 33048.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6484158179990136, "min": -1.0000000521540642, "max": 1.6740112159024463, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 166.48999761790037, "min": -28.99440147727728, "max": 167.3239984586835, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6484158179990136, "min": -1.0000000521540642, "max": 1.6740112159024463, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 166.48999761790037, "min": -28.99440147727728, "max": 167.3239984586835, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.11710243820230647, "min": 0.11710243820230647, "max": 15.859077036380768, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 11.827346258432954, "min": 11.827346258432954, "max": 369.28441870212555, "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": "1708251006", "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": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1708253023" }, "total": 2016.7511919670005, "count": 1, "self": 0.5263509930009604, "children": { "run_training.setup": { "total": 0.04871060299956298, "count": 1, "self": 0.04871060299956298 }, "TrainerController.start_learning": { "total": 2016.176130371, "count": 1, "self": 1.3784278971252206, "children": { "TrainerController._reset_env": { "total": 2.363969076000103, "count": 1, "self": 2.363969076000103 }, "TrainerController.advance": { "total": 2012.3453261768736, "count": 63942, "self": 1.4600268967451484, "children": { "env_step": { "total": 1572.7437265490953, "count": 63942, "self": 1440.5298502861597, "children": { "SubprocessEnvManager._take_step": { "total": 131.3552528938999, "count": 63942, "self": 4.95163457090257, "children": { "TorchPolicy.evaluate": { "total": 126.40361832299732, "count": 62559, "self": 126.40361832299732 } } }, "workers": { "total": 0.8586233690357403, "count": 63942, "self": 0.0, "children": { "worker_root": { "total": 2010.901342087951, "count": 63942, "is_parallel": true, "self": 690.3540399649382, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002151857999706408, "count": 1, "is_parallel": true, "self": 0.0007271609974850435, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014246970022213645, "count": 8, "is_parallel": true, "self": 0.0014246970022213645 } } }, "UnityEnvironment.step": { "total": 0.05260185499992076, "count": 1, "is_parallel": true, "self": 0.0005863749993295642, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005455720001918962, "count": 1, "is_parallel": true, "self": 0.0005455720001918962 }, "communicator.exchange": { "total": 0.04955521800002316, "count": 1, "is_parallel": true, "self": 0.04955521800002316 }, "steps_from_proto": { "total": 0.0019146900003761402, "count": 1, "is_parallel": true, "self": 0.0003910550012733438, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015236349991027964, "count": 8, "is_parallel": true, "self": 0.0015236349991027964 } } } } } } }, "UnityEnvironment.step": { "total": 1320.5473021230127, "count": 63941, "is_parallel": true, "self": 35.92531342201528, "children": { "UnityEnvironment._generate_step_input": { "total": 26.25933700708083, "count": 63941, "is_parallel": true, "self": 26.25933700708083 }, "communicator.exchange": { "total": 1152.9664706589474, "count": 63941, "is_parallel": true, "self": 1152.9664706589474 }, "steps_from_proto": { "total": 105.39618103496923, "count": 63941, "is_parallel": true, "self": 21.262222205221406, "children": { "_process_rank_one_or_two_observation": { "total": 84.13395882974783, "count": 511528, "is_parallel": true, "self": 84.13395882974783 } } } } } } } } } } }, "trainer_advance": { "total": 438.1415727310332, "count": 63942, "self": 2.6525325239490485, "children": { "process_trajectory": { "total": 132.28144910808624, "count": 63942, "self": 130.17975585108707, "children": { "RLTrainer._checkpoint": { "total": 2.1016932569991695, "count": 20, "self": 2.1016932569991695 } } }, "_update_policy": { "total": 303.2075910989979, "count": 235, "self": 235.5791358129636, "children": { "TorchPPOOptimizer.update": { "total": 67.6284552860343, "count": 5748, "self": 67.6284552860343 } } } } } } }, "trainer_threads": { "total": 9.490004231338389e-07, "count": 1, "self": 9.490004231338389e-07 }, "TrainerController._save_models": { "total": 0.08840627200061135, "count": 1, "self": 0.0016691830005584052, "children": { "RLTrainer._checkpoint": { "total": 0.08673708900005295, "count": 1, "self": 0.08673708900005295 } } } } } } }