{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3839421570301056, "min": 0.3839421570301056, "max": 1.3840057849884033, "count": 36 }, "Pyramids.Policy.Entropy.sum": { "value": 11426.1181640625, "min": 11426.1181640625, "max": 41985.19921875, "count": 36 }, "Pyramids.Step.mean": { "value": 1079924.0, "min": 29952.0, "max": 1079924.0, "count": 36 }, "Pyramids.Step.sum": { "value": 1079924.0, "min": 29952.0, "max": 1079924.0, "count": 36 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6972177028656006, "min": -0.1080440953373909, "max": 0.6972177028656006, "count": 36 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 198.70704650878906, "min": -26.03862762451172, "max": 202.53521728515625, "count": 36 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015293323434889317, "min": 0.0012900580186396837, "max": 0.4409424960613251, "count": 36 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.358597278594971, "min": 0.3173542618751526, "max": 104.50337219238281, "count": 36 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06970054509639297, "min": 0.062236538271175285, "max": 0.07377139218511901, "count": 36 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9758076313495014, "min": 0.47454553818191003, "max": 1.0620366521082665, "count": 36 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012039169762006386, "min": 0.000675161943450965, "max": 0.016129291357356128, "count": 36 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1685483766680894, "min": 0.00540129554760772, "max": 0.2419393703603419, "count": 36 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0001935512069115143, "min": 0.0001935512069115143, "max": 0.00029838354339596195, "count": 36 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0027097168967612, "min": 0.0020691136102954665, "max": 0.003927558590813833, "count": 36 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.16451705714285714, "min": 0.16451705714285714, "max": 0.19946118095238097, "count": 36 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.3032388, "min": 1.3897045333333333, "max": 2.7675233000000006, "count": 36 }, "Pyramids.Policy.Beta.mean": { "value": 0.006455254008571429, "min": 0.006455254008571429, "max": 0.009946171977142856, "count": 36 }, "Pyramids.Policy.Beta.sum": { "value": 0.09037355612, "min": 0.06897148288, "max": 0.13092769805, "count": 36 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010369984433054924, "min": 0.010213916189968586, "max": 0.5547193884849548, "count": 36 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14517977833747864, "min": 0.14299482107162476, "max": 3.883035659790039, "count": 36 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 303.6063829787234, "min": 272.50442477876106, "max": 999.0, "count": 36 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28539.0, "min": 15984.0, "max": 33114.0, "count": 36 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6325404104241665, "min": -1.0000000521540642, "max": 1.7274955600763844, "count": 36 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 153.45879857987165, "min": -32.000001668930054, "max": 195.20699828863144, "count": 36 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6325404104241665, "min": -1.0000000521540642, "max": 1.7274955600763844, "count": 36 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 153.45879857987165, "min": -32.000001668930054, "max": 195.20699828863144, "count": 36 }, "Pyramids.Policy.RndReward.mean": { "value": 0.032632508204535934, "min": 0.03137518529122411, "max": 11.203228490427136, "count": 36 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0674557712263777, "min": 3.0674557712263777, "max": 179.25165584683418, "count": 36 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 36 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 36 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1752662820", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1752665198" }, "total": 2377.7998751039995, "count": 1, "self": 0.3462697859995387, "children": { "run_training.setup": { "total": 0.019543620999684208, "count": 1, "self": 0.019543620999684208 }, "TrainerController.start_learning": { "total": 2377.4340616970003, "count": 1, "self": 1.4974488598672906, "children": { "TrainerController._reset_env": { "total": 2.198924530000113, "count": 1, "self": 2.198924530000113 }, "TrainerController.advance": { "total": 2373.609926916134, "count": 70447, "self": 1.5833113511607735, "children": { "env_step": { "total": 1663.1514334170388, "count": 70447, "self": 1503.349375149025, "children": { "SubprocessEnvManager._take_step": { "total": 158.93091554193416, "count": 70447, "self": 5.007721854820375, "children": { "TorchPolicy.evaluate": { "total": 153.92319368711378, "count": 68963, "self": 153.92319368711378 } } }, "workers": { "total": 0.8711427260795972, "count": 70446, "self": 0.0, "children": { "worker_root": { "total": 2371.886998124686, "count": 70446, "is_parallel": true, "self": 988.5799784977999, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018825579991244012, "count": 1, "is_parallel": true, "self": 0.0006047779988875845, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012777800002368167, "count": 8, "is_parallel": true, "self": 0.0012777800002368167 } } }, "UnityEnvironment.step": { "total": 0.04717642000014166, "count": 1, "is_parallel": true, "self": 0.0006024550002621254, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042417900021973765, "count": 1, "is_parallel": true, "self": 0.00042417900021973765 }, "communicator.exchange": { "total": 0.04439154699957726, "count": 1, "is_parallel": true, "self": 0.04439154699957726 }, "steps_from_proto": { "total": 0.0017582390000825399, "count": 1, "is_parallel": true, "self": 0.0003774779979721643, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013807610021103756, "count": 8, "is_parallel": true, "self": 0.0013807610021103756 } } } } } } }, "UnityEnvironment.step": { "total": 1383.3070196268864, "count": 70445, "is_parallel": true, "self": 34.38584017753783, "children": { "UnityEnvironment._generate_step_input": { "total": 23.985653086057027, "count": 70445, "is_parallel": true, "self": 23.985653086057027 }, "communicator.exchange": { "total": 1223.000034940187, "count": 70445, "is_parallel": true, "self": 1223.000034940187 }, "steps_from_proto": { "total": 101.9354914231044, "count": 70445, "is_parallel": true, "self": 20.458428635658493, "children": { "_process_rank_one_or_two_observation": { "total": 81.4770627874459, "count": 563560, "is_parallel": true, "self": 81.4770627874459 } } } } } } } } } } }, "trainer_advance": { "total": 708.8751821479345, "count": 70446, "self": 2.8019618369398813, "children": { "process_trajectory": { "total": 133.0232087760005, "count": 70446, "self": 132.81969475400092, "children": { "RLTrainer._checkpoint": { "total": 0.20351402199958102, "count": 2, "self": 0.20351402199958102 } } }, "_update_policy": { "total": 573.0500115349942, "count": 489, "self": 319.87155223310856, "children": { "TorchPPOOptimizer.update": { "total": 253.1784593018856, "count": 25152, "self": 253.1784593018856 } } } } } } }, "trainer_threads": { "total": 1.2959990272065625e-06, "count": 1, "self": 1.2959990272065625e-06 }, "TrainerController._save_models": { "total": 0.1277600949997577, "count": 1, "self": 0.0018224060004286002, "children": { "RLTrainer._checkpoint": { "total": 0.1259376889993291, "count": 1, "self": 0.1259376889993291 } } } } } } }