{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6309221386909485, "min": 0.5517802238464355, "max": 1.4528251886367798, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18826.716796875, "min": 16588.720703125, "max": 44072.90625, "count": 33 }, "Pyramids.Step.mean": { "value": 989969.0, "min": 29922.0, "max": 989969.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989969.0, "min": 29922.0, "max": 989969.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3538196086883545, "min": -0.11884379386901855, "max": 0.3822344243526459, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 93.05455780029297, "min": -28.641353607177734, "max": 102.05659484863281, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 11.376840591430664, "min": -1.3340771198272705, "max": 11.376840591430664, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2992.109130859375, "min": -349.5281982421875, "max": 2992.109130859375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06857131932132388, "min": 0.06490586224910137, "max": 0.0771923413734024, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9599984704985343, "min": 0.6175387309872192, "max": 1.0512245996667227, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 15.447681779934076, "min": 0.00013634601190398436, "max": 15.447681779934076, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 216.26754491907707, "min": 0.0019088441666557812, "max": 216.26754491907707, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.476076079435708e-06, "min": 7.476076079435708e-06, "max": 0.0002947656392447875, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010466506511209992, "min": 0.00010466506511209992, "max": 0.003633341888886099, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249199285714285, "min": 0.10249199285714285, "max": 0.1982552125, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348878999999999, "min": 1.4348878999999999, "max": 2.6111139000000008, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025895008642857126, "min": 0.00025895008642857126, "max": 0.00982569572875, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036253012099999975, "min": 0.0036253012099999975, "max": 0.12113027861, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015366087667644024, "min": 0.014959233812987804, "max": 0.5141723155975342, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.21512523293495178, "min": 0.2094292789697647, "max": 4.113378524780273, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 511.0483870967742, "min": 468.8, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31685.0, "min": 17360.0, "max": 33010.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2566819377854221, "min": -0.9998774715969639, "max": 1.3660644888877869, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 76.65759820491076, "min": -30.996201619505882, "max": 87.52459850907326, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2566819377854221, "min": -0.9998774715969639, "max": 1.3660644888877869, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 76.65759820491076, "min": -30.996201619505882, "max": 87.52459850907326, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08181005848579292, "min": 0.07692921549799697, "max": 9.933180696641406, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.990413567633368, "min": 4.528399441449437, "max": 178.7972525395453, "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": "1726196157", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1726197912" }, "total": 1755.266822136, "count": 1, "self": 0.3747607980003522, "children": { "run_training.setup": { "total": 0.05434367299949372, "count": 1, "self": 0.05434367299949372 }, "TrainerController.start_learning": { "total": 1754.8377176650001, "count": 1, "self": 1.5318910600963136, "children": { "TrainerController._reset_env": { "total": 1.7687151840000297, "count": 1, "self": 1.7687151840000297 }, "TrainerController.advance": { "total": 1751.4445529459026, "count": 63488, "self": 1.4111253877072159, "children": { "env_step": { "total": 1107.4984813761184, "count": 63488, "self": 949.908416633848, "children": { "SubprocessEnvManager._take_step": { "total": 156.65711663003913, "count": 63488, "self": 4.598251203101427, "children": { "TorchPolicy.evaluate": { "total": 152.0588654269377, "count": 62559, "self": 152.0588654269377 } } }, "workers": { "total": 0.9329481122313155, "count": 63488, "self": 0.0, "children": { "worker_root": { "total": 1752.5316851629177, "count": 63488, "is_parallel": true, "self": 907.5702652098689, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021440210002765525, "count": 1, "is_parallel": true, "self": 0.0007046719993013539, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014393490009751986, "count": 8, "is_parallel": true, "self": 0.0014393490009751986 } } }, "UnityEnvironment.step": { "total": 0.03786469100032264, "count": 1, "is_parallel": true, "self": 0.0004513160010901629, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003284349995738012, "count": 1, "is_parallel": true, "self": 0.0003284349995738012 }, "communicator.exchange": { "total": 0.03581220199976087, "count": 1, "is_parallel": true, "self": 0.03581220199976087 }, "steps_from_proto": { "total": 0.0012727379998977995, "count": 1, "is_parallel": true, "self": 0.0002801259988700622, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009926120010277373, "count": 8, "is_parallel": true, "self": 0.0009926120010277373 } } } } } } }, "UnityEnvironment.step": { "total": 844.9614199530488, "count": 63487, "is_parallel": true, "self": 22.90857045895882, "children": { "UnityEnvironment._generate_step_input": { "total": 14.261316163030642, "count": 63487, "is_parallel": true, "self": 14.261316163030642 }, "communicator.exchange": { "total": 742.4403083370689, "count": 63487, "is_parallel": true, "self": 742.4403083370689 }, "steps_from_proto": { "total": 65.3512249939904, "count": 63487, "is_parallel": true, "self": 14.321769730003325, "children": { "_process_rank_one_or_two_observation": { "total": 51.029455263987074, "count": 507896, "is_parallel": true, "self": 51.029455263987074 } } } } } } } } } } }, "trainer_advance": { "total": 642.534946182077, "count": 63488, "self": 2.749910809024186, "children": { "process_trajectory": { "total": 120.78061354705642, "count": 63488, "self": 120.57818172905718, "children": { "RLTrainer._checkpoint": { "total": 0.2024318179992406, "count": 2, "self": 0.2024318179992406 } } }, "_update_policy": { "total": 519.0044218259964, "count": 457, "self": 288.1165769280642, "children": { "TorchPPOOptimizer.update": { "total": 230.88784489793215, "count": 22767, "self": 230.88784489793215 } } } } } } }, "trainer_threads": { "total": 1.2090004020137712e-06, "count": 1, "self": 1.2090004020137712e-06 }, "TrainerController._save_models": { "total": 0.09255726600076741, "count": 1, "self": 0.0014655570003014873, "children": { "RLTrainer._checkpoint": { "total": 0.09109170900046593, "count": 1, "self": 0.09109170900046593 } } } } } } }