{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2852195203304291, "min": 0.27148833870887756, "max": 1.431126356124878, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8561.1494140625, "min": 8140.30615234375, "max": 43414.6484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989963.0, "min": 29952.0, "max": 989963.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989963.0, "min": 29952.0, "max": 989963.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6735354065895081, "min": -0.08104746043682098, "max": 0.7172265648841858, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 195.99880981445312, "min": -19.532438278198242, "max": 207.99569702148438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.020501714199781418, "min": 0.0008302264614030719, "max": 0.37143102288246155, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.965998649597168, "min": 0.23080295324325562, "max": 88.0291519165039, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06956213456725294, "min": 0.0638889561745427, "max": 0.07430137175833806, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9738698839415412, "min": 0.5096871539934982, "max": 1.114520576375071, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01736705933373222, "min": 0.001485293138367939, "max": 0.01774938083189126, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2431388306722511, "min": 0.017915471827598523, "max": 0.2662407124783689, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.415176099735713e-06, "min": 7.415176099735713e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010381246539629998, "min": 0.00010381246539629998, "max": 0.0036346003884665996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247169285714286, "min": 0.10247169285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346037, "min": 1.3886848, "max": 2.6175454, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002569221164285714, "min": 0.0002569221164285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035969096299999998, "min": 0.0035969096299999998, "max": 0.12117218665999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011578770354390144, "min": 0.011578770354390144, "max": 0.393525093793869, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16210278868675232, "min": 0.16210278868675232, "max": 2.7546756267547607, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 277.2522522522523, "min": 244.8108108108108, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30775.0, "min": 15984.0, "max": 32720.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.685752709954977, "min": -1.0000000521540642, "max": 1.7371657462538899, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 185.43279809504747, "min": -30.600401677191257, "max": 192.82539783418179, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.685752709954977, "min": -1.0000000521540642, "max": 1.7371657462538899, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 185.43279809504747, "min": -30.600401677191257, "max": 192.82539783418179, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03313139912894588, "min": 0.03309181056114916, "max": 7.53322974499315, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.644453904184047, "min": 3.644453904184047, "max": 120.5316759198904, "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": "1754733611", "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": "1754735990" }, "total": 2378.859708934, "count": 1, "self": 0.5259848329997112, "children": { "run_training.setup": { "total": 0.021898022000186756, "count": 1, "self": 0.021898022000186756 }, "TrainerController.start_learning": { "total": 2378.311826079, "count": 1, "self": 1.4477438048434124, "children": { "TrainerController._reset_env": { "total": 2.184242827000162, "count": 1, "self": 2.184242827000162 }, "TrainerController.advance": { "total": 2374.5997482401576, "count": 64349, "self": 1.4374085361628204, "children": { "env_step": { "total": 1707.4579113309305, "count": 64349, "self": 1555.7216094239552, "children": { "SubprocessEnvManager._take_step": { "total": 150.89169655594424, "count": 64349, "self": 4.831130240961102, "children": { "TorchPolicy.evaluate": { "total": 146.06056631498313, "count": 62567, "self": 146.06056631498313 } } }, "workers": { "total": 0.8446053510310776, "count": 64349, "self": 0.0, "children": { "worker_root": { "total": 2373.1133421140157, "count": 64349, "is_parallel": true, "self": 933.1241265969898, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002695902000141359, "count": 1, "is_parallel": true, "self": 0.0008160320007846167, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018798699993567425, "count": 8, "is_parallel": true, "self": 0.0018798699993567425 } } }, "UnityEnvironment.step": { "total": 0.0487669599997389, "count": 1, "is_parallel": true, "self": 0.0005737160004173347, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000561637999908271, "count": 1, "is_parallel": true, "self": 0.000561637999908271 }, "communicator.exchange": { "total": 0.0457367159997375, "count": 1, "is_parallel": true, "self": 0.0457367159997375 }, "steps_from_proto": { "total": 0.0018948899996757973, "count": 1, "is_parallel": true, "self": 0.00038697599893566803, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015079140007401293, "count": 8, "is_parallel": true, "self": 0.0015079140007401293 } } } } } } }, "UnityEnvironment.step": { "total": 1439.989215517026, "count": 64348, "is_parallel": true, "self": 31.93648335197804, "children": { "UnityEnvironment._generate_step_input": { "total": 23.04104659102086, "count": 64348, "is_parallel": true, "self": 23.04104659102086 }, "communicator.exchange": { "total": 1287.4374927850222, "count": 64348, "is_parallel": true, "self": 1287.4374927850222 }, "steps_from_proto": { "total": 97.57419278900488, "count": 64348, "is_parallel": true, "self": 19.569018990025143, "children": { "_process_rank_one_or_two_observation": { "total": 78.00517379897974, "count": 514784, "is_parallel": true, "self": 78.00517379897974 } } } } } } } } } } }, "trainer_advance": { "total": 665.7044283730643, "count": 64349, "self": 2.7715778841002248, "children": { "process_trajectory": { "total": 130.39890288897004, "count": 64349, "self": 130.20460815296974, "children": { "RLTrainer._checkpoint": { "total": 0.19429473600030178, "count": 2, "self": 0.19429473600030178 } } }, "_update_policy": { "total": 532.533947599994, "count": 456, "self": 296.97010616897114, "children": { "TorchPPOOptimizer.update": { "total": 235.56384143102287, "count": 22821, "self": 235.56384143102287 } } } } } } }, "trainer_threads": { "total": 1.0019994078902528e-06, "count": 1, "self": 1.0019994078902528e-06 }, "TrainerController._save_models": { "total": 0.08009020499957842, "count": 1, "self": 0.0013597469996966538, "children": { "RLTrainer._checkpoint": { "total": 0.07873045799988176, "count": 1, "self": 0.07873045799988176 } } } } } } }