{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4796457886695862, "min": 0.4796457886695862, "max": 1.3948088884353638, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14374.025390625, "min": 14374.025390625, "max": 42312.921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989999.0, "min": 29952.0, "max": 989999.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989999.0, "min": 29952.0, "max": 989999.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5406160950660706, "min": -0.10442328453063965, "max": 0.5406160950660706, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 148.66941833496094, "min": -25.270435333251953, "max": 148.66941833496094, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.020334385335445404, "min": -0.01262757834047079, "max": 0.5951128602027893, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.59195613861084, "min": -3.3084254264831543, "max": 141.041748046875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06793769446973812, "min": 0.06600451514499987, "max": 0.07428393240150487, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9511277225763336, "min": 0.48978102573273224, "max": 1.0764315729166436, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015570436293594812, "min": 0.0008631827389785607, "max": 0.01774840843574778, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21798610811032737, "min": 0.01122137560672129, "max": 0.23055001915296697, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.447276089035714e-06, "min": 7.447276089035714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001042618652465, "min": 0.0001042618652465, "max": 0.0036329086890305, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248239285714288, "min": 0.10248239285714288, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347535000000002, "min": 1.3886848, "max": 2.6109695, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002579910464285715, "min": 0.0002579910464285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003611874650000001, "min": 0.003611874650000001, "max": 0.12111585305000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009840461425483227, "min": 0.009699009358882904, "max": 0.5861557126045227, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13776646554470062, "min": 0.13578613102436066, "max": 4.103089809417725, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 362.3658536585366, "min": 341.48837209302326, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29714.0, "min": 15984.0, "max": 33826.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5644438820096052, "min": -1.0000000521540642, "max": 1.6352488097063331, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 128.28439832478762, "min": -29.270601630210876, "max": 140.63139763474464, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5644438820096052, "min": -1.0000000521540642, "max": 1.6352488097063331, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 128.28439832478762, "min": -29.270601630210876, "max": 140.63139763474464, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0370946939453971, "min": 0.03521266605956805, "max": 13.707543040625751, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0417649035225622, "min": 2.8207042317371815, "max": 219.32068865001202, "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": "1761515006", "python_version": "3.10.12 (main, Jul 26 2023, 13:20:36) [Clang 16.0.3 ]", "command_line_arguments": "/content/myenv/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": "1761517177" }, "total": 2171.537159658, "count": 1, "self": 0.7504625589999705, "children": { "run_training.setup": { "total": 0.018704929000023185, "count": 1, "self": 0.018704929000023185 }, "TrainerController.start_learning": { "total": 2170.76799217, "count": 1, "self": 1.4181678309951167, "children": { "TrainerController._reset_env": { "total": 2.1863718069998868, "count": 1, "self": 2.1863718069998868 }, "TrainerController.advance": { "total": 2167.0582597580046, "count": 63789, "self": 1.4720493519203046, "children": { "env_step": { "total": 1495.3098172350012, "count": 63789, "self": 1343.5759227789397, "children": { "SubprocessEnvManager._take_step": { "total": 150.8913739800023, "count": 63789, "self": 4.677072216966508, "children": { "TorchPolicy.evaluate": { "total": 146.2143017630358, "count": 62570, "self": 146.2143017630358 } } }, "workers": { "total": 0.8425204760592351, "count": 63789, "self": 0.0, "children": { "worker_root": { "total": 2164.5760396200235, "count": 63789, "is_parallel": true, "self": 934.9624413190188, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002016105999928186, "count": 1, "is_parallel": true, "self": 0.0007286009997642395, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012875050001639465, "count": 8, "is_parallel": true, "self": 0.0012875050001639465 } } }, "UnityEnvironment.step": { "total": 0.08781074400008038, "count": 1, "is_parallel": true, "self": 0.002598505000150908, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048072399999909976, "count": 1, "is_parallel": true, "self": 0.00048072399999909976 }, "communicator.exchange": { "total": 0.07897830699994302, "count": 1, "is_parallel": true, "self": 0.07897830699994302 }, "steps_from_proto": { "total": 0.005753207999987353, "count": 1, "is_parallel": true, "self": 0.00240213600000061, "children": { "_process_rank_one_or_two_observation": { "total": 0.0033510719999867433, "count": 8, "is_parallel": true, "self": 0.0033510719999867433 } } } } } } }, "UnityEnvironment.step": { "total": 1229.6135983010047, "count": 63788, "is_parallel": true, "self": 32.808205314039924, "children": { "UnityEnvironment._generate_step_input": { "total": 23.711422900996013, "count": 63788, "is_parallel": true, "self": 23.711422900996013 }, "communicator.exchange": { "total": 1066.962537296006, "count": 63788, "is_parallel": true, "self": 1066.962537296006 }, "steps_from_proto": { "total": 106.13143278996267, "count": 63788, "is_parallel": true, "self": 23.273504333903247, "children": { "_process_rank_one_or_two_observation": { "total": 82.85792845605943, "count": 510304, "is_parallel": true, "self": 82.85792845605943 } } } } } } } } } } }, "trainer_advance": { "total": 670.2763931710831, "count": 63789, "self": 2.657870988121431, "children": { "process_trajectory": { "total": 129.07817657896635, "count": 63789, "self": 128.85205381096625, "children": { "RLTrainer._checkpoint": { "total": 0.22612276800009568, "count": 2, "self": 0.22612276800009568 } } }, "_update_policy": { "total": 538.5403456039953, "count": 456, "self": 304.1133765709783, "children": { "TorchPPOOptimizer.update": { "total": 234.42696903301703, "count": 22815, "self": 234.42696903301703 } } } } } } }, "trainer_threads": { "total": 1.4390002434083726e-06, "count": 1, "self": 1.4390002434083726e-06 }, "TrainerController._save_models": { "total": 0.10519133500019962, "count": 1, "self": 0.001561605000460986, "children": { "RLTrainer._checkpoint": { "total": 0.10362972999973863, "count": 1, "self": 0.10362972999973863 } } } } } } }