{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.47833681106567383, "min": 0.47833681106567383, "max": 1.4127907752990723, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14212.34375, "min": 14212.34375, "max": 42858.421875, "count": 33 }, "Pyramids.Step.mean": { "value": 989898.0, "min": 29952.0, "max": 989898.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989898.0, "min": 29952.0, "max": 989898.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5738986134529114, "min": -0.11482176184654236, "max": 0.6057373285293579, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 160.6916046142578, "min": -27.67204475402832, "max": 172.02940368652344, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.06816668808460236, "min": -0.08588041365146637, "max": 0.294450581073761, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -19.086671829223633, "min": -24.04651641845703, "max": 70.66813659667969, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06827534682053651, "min": 0.06451852188495519, "max": 0.07467557045548721, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9558548554875111, "min": 0.4919867245130837, "max": 1.0879309351702093, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017974939744731057, "min": 0.00032881614229307137, "max": 0.018102450249508757, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2516491564262348, "min": 0.0036169775652237853, "max": 0.26306811121564044, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.409326101685716e-06, "min": 7.409326101685716e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010373056542360001, "min": 0.00010373056542360001, "max": 0.0032594810135064, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246974285714286, "min": 0.10246974285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345764, "min": 1.3691136000000002, "max": 2.3864935999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002567273114285715, "min": 0.0002567273114285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003594182360000001, "min": 0.003594182360000001, "max": 0.10867071063999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011203487403690815, "min": 0.010594257153570652, "max": 0.4041219651699066, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15684881806373596, "min": 0.15380680561065674, "max": 2.8288538455963135, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 317.7604166666667, "min": 305.8484848484849, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30505.0, "min": 15984.0, "max": 32950.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.640556237893179, "min": -1.0000000521540642, "max": 1.6537333160939842, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 157.4933988377452, "min": -32.000001668930054, "max": 163.71959829330444, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.640556237893179, "min": -1.0000000521540642, "max": 1.6537333160939842, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 157.4933988377452, "min": -32.000001668930054, "max": 163.71959829330444, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03656285343959098, "min": 0.03515216328878064, "max": 8.22155408281833, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.510033930200734, "min": 3.30839214849766, "max": 131.54486532509327, "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": "1758803934", "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": "1758806017" }, "total": 2083.5278802860003, "count": 1, "self": 0.4794890360003592, "children": { "run_training.setup": { "total": 0.023915801999919495, "count": 1, "self": 0.023915801999919495 }, "TrainerController.start_learning": { "total": 2083.024475448, "count": 1, "self": 1.2242356310325704, "children": { "TrainerController._reset_env": { "total": 2.09876038099992, "count": 1, "self": 2.09876038099992 }, "TrainerController.advance": { "total": 2079.625226027967, "count": 63739, "self": 1.2903559489141117, "children": { "env_step": { "total": 1438.3445771150027, "count": 63739, "self": 1298.6480151209728, "children": { "SubprocessEnvManager._take_step": { "total": 138.96164424305653, "count": 63739, "self": 4.327730657018719, "children": { "TorchPolicy.evaluate": { "total": 134.6339135860378, "count": 62565, "self": 134.6339135860378 } } }, "workers": { "total": 0.7349177509734091, "count": 63739, "self": 0.0, "children": { "worker_root": { "total": 2076.032194760017, "count": 63739, "is_parallel": true, "self": 885.9763994719792, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001795390000097541, "count": 1, "is_parallel": true, "self": 0.0005608650001249771, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012345249999725638, "count": 8, "is_parallel": true, "self": 0.0012345249999725638 } } }, "UnityEnvironment.step": { "total": 0.05246435599997312, "count": 1, "is_parallel": true, "self": 0.0005611330000192538, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005008910000015021, "count": 1, "is_parallel": true, "self": 0.0005008910000015021 }, "communicator.exchange": { "total": 0.04984294499990938, "count": 1, "is_parallel": true, "self": 0.04984294499990938 }, "steps_from_proto": { "total": 0.0015593870000429888, "count": 1, "is_parallel": true, "self": 0.00033005399973262683, "children": { "_process_rank_one_or_two_observation": { "total": 0.001229333000310362, "count": 8, "is_parallel": true, "self": 0.001229333000310362 } } } } } } }, "UnityEnvironment.step": { "total": 1190.0557952880376, "count": 63738, "is_parallel": true, "self": 31.758557790966734, "children": { "UnityEnvironment._generate_step_input": { "total": 21.413147288060372, "count": 63738, "is_parallel": true, "self": 21.413147288060372 }, "communicator.exchange": { "total": 1038.2726261190355, "count": 63738, "is_parallel": true, "self": 1038.2726261190355 }, "steps_from_proto": { "total": 98.61146408997502, "count": 63738, "is_parallel": true, "self": 20.49290719715964, "children": { "_process_rank_one_or_two_observation": { "total": 78.11855689281538, "count": 509904, "is_parallel": true, "self": 78.11855689281538 } } } } } } } } } } }, "trainer_advance": { "total": 639.99029296405, "count": 63739, "self": 2.272101673033376, "children": { "process_trajectory": { "total": 118.06684945202414, "count": 63739, "self": 117.83400190802377, "children": { "RLTrainer._checkpoint": { "total": 0.23284754400037855, "count": 2, "self": 0.23284754400037855 } } }, "_update_policy": { "total": 519.6513418389925, "count": 438, "self": 289.8265280149694, "children": { "TorchPPOOptimizer.update": { "total": 229.82481382402307, "count": 22878, "self": 229.82481382402307 } } } } } } }, "trainer_threads": { "total": 9.170003067993093e-07, "count": 1, "self": 9.170003067993093e-07 }, "TrainerController._save_models": { "total": 0.07625249100010478, "count": 1, "self": 0.0010694880002120044, "children": { "RLTrainer._checkpoint": { "total": 0.07518300299989278, "count": 1, "self": 0.07518300299989278 } } } } } } }