{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.37083908915519714, "min": 0.37083908915519714, "max": 1.4725401401519775, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11089.572265625, "min": 11089.572265625, "max": 44670.9765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989940.0, "min": 29952.0, "max": 989940.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989940.0, "min": 29952.0, "max": 989940.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6173298358917236, "min": -0.09662697464227676, "max": 0.7420381307601929, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 172.85235595703125, "min": -23.38372802734375, "max": 215.46006774902344, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.04758405685424805, "min": -0.015613943338394165, "max": 0.44422441720962524, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 13.323535919189453, "min": -4.325062274932861, "max": 105.28118896484375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0697656320643589, "min": 0.06489190768220766, "max": 0.07253667032897772, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9767188489010247, "min": 0.49882043616701693, "max": 1.0880500549346657, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014289842597333648, "min": 0.0005608458581124203, "max": 0.016347611260287175, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20005779636267107, "min": 0.006730150297349044, "max": 0.22886655764402045, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.682968867614284e-06, "min": 7.682968867614284e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010756156414659997, "min": 0.00010756156414659997, "max": 0.0036332221889259996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256095714285715, "min": 0.10256095714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358534, "min": 1.3886848, "max": 2.6110740000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026583961857142854, "min": 0.00026583961857142854, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00372175466, "min": 0.00372175466, "max": 0.12112629259999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013717937283217907, "min": 0.013525714166462421, "max": 0.49739137291908264, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19205112755298615, "min": 0.18935999274253845, "max": 3.4817395210266113, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 309.1170212765957, "min": 247.43859649122808, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29057.0, "min": 15984.0, "max": 32594.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6713347223244215, "min": -1.0000000521540642, "max": 1.7525613934063076, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 158.77679862082005, "min": -30.623601660132408, "max": 199.79199884831905, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6713347223244215, "min": -1.0000000521540642, "max": 1.7525613934063076, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 158.77679862082005, "min": -30.623601660132408, "max": 199.79199884831905, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04370384230768602, "min": 0.036626345024591216, "max": 10.152976502664387, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.151865019230172, "min": 4.151865019230172, "max": 162.4476240426302, "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": "1789116807", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/usr/local/miniconda/envs/py310/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": "1789119682" }, "total": 2874.9987712559996, "count": 1, "self": 0.4811727299984341, "children": { "run_training.setup": { "total": 0.02157741100018029, "count": 1, "self": 0.02157741100018029 }, "TrainerController.start_learning": { "total": 2874.496021115001, "count": 1, "self": 1.8642979986352657, "children": { "TrainerController._reset_env": { "total": 2.4090765020000617, "count": 1, "self": 2.4090765020000617 }, "TrainerController.advance": { "total": 2870.145304890366, "count": 64299, "self": 1.9378966415970353, "children": { "env_step": { "total": 2190.0924886328394, "count": 64299, "self": 2002.0773781440002, "children": { "SubprocessEnvManager._take_step": { "total": 186.85435104094995, "count": 64299, "self": 5.553393084811432, "children": { "TorchPolicy.evaluate": { "total": 181.30095795613852, "count": 62553, "self": 181.30095795613852 } } }, "workers": { "total": 1.160759447889177, "count": 64299, "self": 0.0, "children": { "worker_root": { "total": 2867.785053440197, "count": 64299, "is_parallel": true, "self": 1014.9531230962875, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019641839999167132, "count": 1, "is_parallel": true, "self": 0.0007247820012707962, "children": { "_process_rank_one_or_two_observation": { "total": 0.001239401998645917, "count": 8, "is_parallel": true, "self": 0.001239401998645917 } } }, "UnityEnvironment.step": { "total": 0.06504805300028238, "count": 1, "is_parallel": true, "self": 0.0005477149998114328, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004882220000581583, "count": 1, "is_parallel": true, "self": 0.0004882220000581583 }, "communicator.exchange": { "total": 0.061952207000103954, "count": 1, "is_parallel": true, "self": 0.061952207000103954 }, "steps_from_proto": { "total": 0.002059909000308835, "count": 1, "is_parallel": true, "self": 0.000551155001630832, "children": { "_process_rank_one_or_two_observation": { "total": 0.001508753998678003, "count": 8, "is_parallel": true, "self": 0.001508753998678003 } } } } } } }, "UnityEnvironment.step": { "total": 1852.8319303439093, "count": 64298, "is_parallel": true, "self": 38.677466602604, "children": { "UnityEnvironment._generate_step_input": { "total": 26.36732579215368, "count": 64298, "is_parallel": true, "self": 26.36732579215368 }, "communicator.exchange": { "total": 1657.1159118299383, "count": 64298, "is_parallel": true, "self": 1657.1159118299383 }, "steps_from_proto": { "total": 130.67122611921332, "count": 64298, "is_parallel": true, "self": 27.741246361725644, "children": { "_process_rank_one_or_two_observation": { "total": 102.92997975748767, "count": 514384, "is_parallel": true, "self": 102.92997975748767 } } } } } } } } } } }, "trainer_advance": { "total": 678.1149196159295, "count": 64299, "self": 3.58972009491481, "children": { "process_trajectory": { "total": 128.98444008398565, "count": 64299, "self": 128.74126521798735, "children": { "RLTrainer._checkpoint": { "total": 0.24317486599829863, "count": 2, "self": 0.24317486599829863 } } }, "_update_policy": { "total": 545.540759437029, "count": 455, "self": 294.96509886304284, "children": { "TorchPPOOptimizer.update": { "total": 250.57566057398617, "count": 22800, "self": 250.57566057398617 } } } } } } }, "trainer_threads": { "total": 9.960003808373585e-07, "count": 1, "self": 9.960003808373585e-07 }, "TrainerController._save_models": { "total": 0.07734072799939895, "count": 1, "self": 0.0009278329998778645, "children": { "RLTrainer._checkpoint": { "total": 0.07641289499952109, "count": 1, "self": 0.07641289499952109 } } } } } } }