{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5008918642997742, "min": 0.49415332078933716, "max": 1.3627724647521973, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15203.0703125, "min": 14792.494140625, "max": 41341.06640625, "count": 33 }, "Pyramids.Step.mean": { "value": 989991.0, "min": 29931.0, "max": 989991.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989991.0, "min": 29931.0, "max": 989991.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.25935497879981995, "min": -0.10566291958093643, "max": 0.25935497879981995, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 67.691650390625, "min": -25.359100341796875, "max": 67.691650390625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.018526701256632805, "min": 0.0023067202419042587, "max": 0.29651781916618347, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.8354692459106445, "min": 0.5697599053382874, "max": 71.4607925415039, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0695112546441926, "min": 0.06464130459609854, "max": 0.07375549260014057, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9731575650186963, "min": 0.5776933278763909, "max": 1.1063323890021086, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010601841838437832, "min": 0.00025714954498064045, "max": 0.011701165912589724, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.14842578573812965, "min": 0.003600093629728966, "max": 0.16381632277625613, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4615475128500035e-06, "min": 7.4615475128500035e-06, "max": 0.0002949140641953125, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010446166517990005, "min": 0.00010446166517990005, "max": 0.0036330592889802994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248715, "min": 0.10248715, "max": 0.1983046875, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348201, "min": 1.4348201, "max": 2.6110197000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025846628500000016, "min": 0.00025846628500000016, "max": 0.00983063828125, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036185279900000024, "min": 0.0036185279900000024, "max": 0.12112086802999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013065754435956478, "min": 0.012878145091235638, "max": 0.45404013991355896, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18292056024074554, "min": 0.18292056024074554, "max": 3.6323211193084717, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 580.6666666666666, "min": 556.0185185185185, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29614.0, "min": 16985.0, "max": 32999.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9485764440660384, "min": -0.9998774711162813, "max": 1.1105481299261253, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 48.377398647367954, "min": -31.990401655435562, "max": 59.96959901601076, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9485764440660384, "min": -0.9998774711162813, "max": 1.1105481299261253, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 48.377398647367954, "min": -31.990401655435562, "max": 59.96959901601076, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07846601289245025, "min": 0.07568692759162297, "max": 8.942541084355778, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.001766657514963, "min": 3.9502898525679484, "max": 160.965739518404, "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": "1793349241", "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": "1793351363" }, "total": 2121.72546598, "count": 1, "self": 0.4885409050002636, "children": { "run_training.setup": { "total": 0.03007370999989689, "count": 1, "self": 0.03007370999989689 }, "TrainerController.start_learning": { "total": 2121.206851365, "count": 1, "self": 1.561541146019863, "children": { "TrainerController._reset_env": { "total": 3.2414722549999624, "count": 1, "self": 3.2414722549999624 }, "TrainerController.advance": { "total": 2116.32084823498, "count": 63368, "self": 1.5162221879845674, "children": { "env_step": { "total": 1474.5053117590314, "count": 63368, "self": 1311.0221018100663, "children": { "SubprocessEnvManager._take_step": { "total": 162.5368631269771, "count": 63368, "self": 4.850042683001448, "children": { "TorchPolicy.evaluate": { "total": 157.68682044397565, "count": 62569, "self": 157.68682044397565 } } }, "workers": { "total": 0.9463468219880724, "count": 63368, "self": 0.0, "children": { "worker_root": { "total": 2117.725140895036, "count": 63368, "is_parallel": true, "self": 923.5151120781036, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0059868509999887465, "count": 1, "is_parallel": true, "self": 0.004498529999864331, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014883210001244151, "count": 8, "is_parallel": true, "self": 0.0014883210001244151 } } }, "UnityEnvironment.step": { "total": 0.05340095500014286, "count": 1, "is_parallel": true, "self": 0.0005726420001792576, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046901999985493603, "count": 1, "is_parallel": true, "self": 0.00046901999985493603 }, "communicator.exchange": { "total": 0.048710540000001856, "count": 1, "is_parallel": true, "self": 0.048710540000001856 }, "steps_from_proto": { "total": 0.003648753000106808, "count": 1, "is_parallel": true, "self": 0.00037468699997589283, "children": { "_process_rank_one_or_two_observation": { "total": 0.003274066000130915, "count": 8, "is_parallel": true, "self": 0.003274066000130915 } } } } } } }, "UnityEnvironment.step": { "total": 1194.2100288169324, "count": 63367, "is_parallel": true, "self": 34.868732258018554, "children": { "UnityEnvironment._generate_step_input": { "total": 24.372866424923586, "count": 63367, "is_parallel": true, "self": 24.372866424923586 }, "communicator.exchange": { "total": 1028.9486129289735, "count": 63367, "is_parallel": true, "self": 1028.9486129289735 }, "steps_from_proto": { "total": 106.0198172050168, "count": 63367, "is_parallel": true, "self": 21.479804429874548, "children": { "_process_rank_one_or_two_observation": { "total": 84.54001277514226, "count": 506936, "is_parallel": true, "self": 84.54001277514226 } } } } } } } } } } }, "trainer_advance": { "total": 640.2993142879639, "count": 63368, "self": 3.0233722599393786, "children": { "process_trajectory": { "total": 112.1310846300239, "count": 63368, "self": 111.78472455202427, "children": { "RLTrainer._checkpoint": { "total": 0.3463600779996341, "count": 2, "self": 0.3463600779996341 } } }, "_update_policy": { "total": 525.1448573980006, "count": 456, "self": 288.6328091989467, "children": { "TorchPPOOptimizer.update": { "total": 236.51204819905388, "count": 22755, "self": 236.51204819905388 } } } } } } }, "trainer_threads": { "total": 9.840000529948156e-07, "count": 1, "self": 9.840000529948156e-07 }, "TrainerController._save_models": { "total": 0.082988744999966, "count": 1, "self": 0.0011167989996465622, "children": { "RLTrainer._checkpoint": { "total": 0.08187194600031944, "count": 1, "self": 0.08187194600031944 } } } } } } }