{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2573873996734619, "min": 0.2573873996734619, "max": 1.3851722478866577, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7676.32177734375, "min": 7676.32177734375, "max": 42020.5859375, "count": 33 }, "Pyramids.Step.mean": { "value": 989909.0, "min": 29952.0, "max": 989909.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989909.0, "min": 29952.0, "max": 989909.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6522399187088013, "min": -0.11068243533372879, "max": 0.7249375581741333, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 187.8450927734375, "min": -26.78514862060547, "max": 208.78201293945312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.04634951055049896, "min": -0.044027965515851974, "max": 0.8621852397918701, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 13.34865951538086, "min": -12.283802032470703, "max": 208.64883422851562, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0677992049724086, "min": 0.06532868636644534, "max": 0.07330277443785843, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9491888696137204, "min": 0.5089722511727542, "max": 1.0995416165678764, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01686094892812901, "min": 0.0010929993404196596, "max": 0.019789959558717124, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2360532849938061, "min": 0.014202343313803139, "max": 0.26130202890878235, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.408404673421429e-06, "min": 7.408404673421429e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010371766542790001, "min": 0.00010371766542790001, "max": 0.0035100566299812, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246943571428571, "min": 0.10246943571428571, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345721, "min": 1.3886848, "max": 2.6175663, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002566966278571429, "min": 0.0002566966278571429, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035937527900000007, "min": 0.0035937527900000007, "max": 0.11702487812000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.017587047070264816, "min": 0.016965989023447037, "max": 0.7480431795120239, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.24621866643428802, "min": 0.23752383887767792, "max": 5.236302375793457, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 281.1089108910891, "min": 255.48760330578511, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28392.0, "min": 15984.0, "max": 33128.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.699085127894241, "min": -1.0000000521540642, "max": 1.7279768483944176, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 171.60759791731834, "min": -28.554401606321335, "max": 209.08519865572453, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.699085127894241, "min": -1.0000000521540642, "max": 1.7279768483944176, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 171.60759791731834, "min": -28.554401606321335, "max": 209.08519865572453, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05158998766489843, "min": 0.04476348276674355, "max": 16.028654161840677, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.210588754154742, "min": 5.210588754154742, "max": 256.45846658945084, "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": "1735597036", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./ml-agents/training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --torch-device cpu", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1735600381" }, "total": 3345.17673046, "count": 1, "self": 0.6509073090001039, "children": { "run_training.setup": { "total": 0.07661089700002321, "count": 1, "self": 0.07661089700002321 }, "TrainerController.start_learning": { "total": 3344.4492122539996, "count": 1, "self": 2.4096931690082783, "children": { "TrainerController._reset_env": { "total": 6.128095167000083, "count": 1, "self": 6.128095167000083 }, "TrainerController.advance": { "total": 3335.8292106719914, "count": 64426, "self": 2.5395324499459093, "children": { "env_step": { "total": 2259.9660715740047, "count": 64426, "self": 2103.6373085420546, "children": { "SubprocessEnvManager._take_step": { "total": 155.01667859797874, "count": 64426, "self": 6.57653955197452, "children": { "TorchPolicy.evaluate": { "total": 148.44013904600422, "count": 62564, "self": 148.44013904600422 } } }, "workers": { "total": 1.3120844339715632, "count": 64426, "self": 0.0, "children": { "worker_root": { "total": 3337.364715634015, "count": 64426, "is_parallel": true, "self": 1404.5940921109923, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029317990000663485, "count": 1, "is_parallel": true, "self": 0.000862854000047264, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020689450000190845, "count": 8, "is_parallel": true, "self": 0.0020689450000190845 } } }, "UnityEnvironment.step": { "total": 0.07241654599999947, "count": 1, "is_parallel": true, "self": 0.0007955519999995886, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005202199999985169, "count": 1, "is_parallel": true, "self": 0.0005202199999985169 }, "communicator.exchange": { "total": 0.06905683000002227, "count": 1, "is_parallel": true, "self": 0.06905683000002227 }, "steps_from_proto": { "total": 0.002043943999979092, "count": 1, "is_parallel": true, "self": 0.0004096900000831738, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016342539998959182, "count": 8, "is_parallel": true, "self": 0.0016342539998959182 } } } } } } }, "UnityEnvironment.step": { "total": 1932.7706235230226, "count": 64425, "is_parallel": true, "self": 48.04160234707933, "children": { "UnityEnvironment._generate_step_input": { "total": 29.577883611000857, "count": 64425, "is_parallel": true, "self": 29.577883611000857 }, "communicator.exchange": { "total": 1726.7833993949835, "count": 64425, "is_parallel": true, "self": 1726.7833993949835 }, "steps_from_proto": { "total": 128.3677381699589, "count": 64425, "is_parallel": true, "self": 27.54524429800358, "children": { "_process_rank_one_or_two_observation": { "total": 100.82249387195532, "count": 515400, "is_parallel": true, "self": 100.82249387195532 } } } } } } } } } } }, "trainer_advance": { "total": 1073.3236066480408, "count": 64426, "self": 4.238414744981583, "children": { "process_trajectory": { "total": 166.3746423860647, "count": 64426, "self": 166.07808639506482, "children": { "RLTrainer._checkpoint": { "total": 0.2965559909998774, "count": 2, "self": 0.2965559909998774 } } }, "_update_policy": { "total": 902.7105495169944, "count": 455, "self": 366.60458685299193, "children": { "TorchPPOOptimizer.update": { "total": 536.1059626640025, "count": 22839, "self": 536.1059626640025 } } } } } } }, "trainer_threads": { "total": 1.27099974633893e-06, "count": 1, "self": 1.27099974633893e-06 }, "TrainerController._save_models": { "total": 0.08221197500006383, "count": 1, "self": 0.0019303680001030443, "children": { "RLTrainer._checkpoint": { "total": 0.08028160699996079, "count": 1, "self": 0.08028160699996079 } } } } } } }