{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4654870927333832, "min": 0.4654870927333832, "max": 1.4581407308578491, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14135.912109375, "min": 14124.5634765625, "max": 44234.15625, "count": 33 }, "Pyramids.Step.mean": { "value": 989992.0, "min": 29952.0, "max": 989992.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989992.0, "min": 29952.0, "max": 989992.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.44167011976242065, "min": -0.19474275410175323, "max": 0.44167011976242065, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 120.13426971435547, "min": -46.15403366088867, "max": 120.13426971435547, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.008820760063827038, "min": -0.008820760063827038, "max": 0.5793318152427673, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.3992466926574707, "min": -2.3992466926574707, "max": 137.3016357421875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07058378458087745, "min": 0.06584759708412878, "max": 0.07411003576707148, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0587567687131618, "min": 0.4762111773838867, "max": 1.0587567687131618, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017376152395283697, "min": 0.00034545916569860436, "max": 0.017376152395283697, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2606422859292555, "min": 0.0034545916569860436, "max": 0.2606422859292555, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.51675749444667e-06, "min": 7.51675749444667e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011275136241670005, "min": 0.00011275136241670005, "max": 0.0031388825537058997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250555333333335, "min": 0.10250555333333335, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375833, "min": 1.3886848, "max": 2.4020898, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026030477800000014, "min": 0.00026030477800000014, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039045716700000024, "min": 0.0039045716700000024, "max": 0.10465478058999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010420089587569237, "min": 0.010420089587569237, "max": 0.4487457275390625, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.156301349401474, "min": 0.14787952601909637, "max": 3.1412200927734375, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 404.012987012987, "min": 404.012987012987, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31109.0, "min": 15984.0, "max": 32255.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5180493347443544, "min": -1.0000000521540642, "max": 1.5180493347443544, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 116.88979877531528, "min": -31.998401656746864, "max": 116.88979877531528, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5180493347443544, "min": -1.0000000521540642, "max": 1.5180493347443544, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 116.88979877531528, "min": -31.998401656746864, "max": 116.88979877531528, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.043499317464530965, "min": 0.043499317464530965, "max": 9.53220378421247, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3494474447688845, "min": 3.0434805232071085, "max": 152.51526054739952, "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": "1754173362", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1754175439" }, "total": 2076.432912056, "count": 1, "self": 0.4792193060002319, "children": { "run_training.setup": { "total": 0.019335599999976694, "count": 1, "self": 0.019335599999976694 }, "TrainerController.start_learning": { "total": 2075.93435715, "count": 1, "self": 1.2358541890325796, "children": { "TrainerController._reset_env": { "total": 2.1664041919998454, "count": 1, "self": 2.1664041919998454 }, "TrainerController.advance": { "total": 2072.455682732967, "count": 63592, "self": 1.2876759839177794, "children": { "env_step": { "total": 1429.5913795540127, "count": 63592, "self": 1286.5433565610829, "children": { "SubprocessEnvManager._take_step": { "total": 142.29521544195495, "count": 63592, "self": 4.338840300029915, "children": { "TorchPolicy.evaluate": { "total": 137.95637514192504, "count": 62566, "self": 137.95637514192504 } } }, "workers": { "total": 0.7528075509749215, "count": 63592, "self": 0.0, "children": { "worker_root": { "total": 2070.992183068024, "count": 63592, "is_parallel": true, "self": 893.9965204869445, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001807401999940339, "count": 1, "is_parallel": true, "self": 0.000592136000705068, "children": { "_process_rank_one_or_two_observation": { "total": 0.001215265999235271, "count": 8, "is_parallel": true, "self": 0.001215265999235271 } } }, "UnityEnvironment.step": { "total": 0.048128037999958906, "count": 1, "is_parallel": true, "self": 0.0004953140000907297, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004383880000204954, "count": 1, "is_parallel": true, "self": 0.0004383880000204954 }, "communicator.exchange": { "total": 0.045602971999869624, "count": 1, "is_parallel": true, "self": 0.045602971999869624 }, "steps_from_proto": { "total": 0.0015913639999780571, "count": 1, "is_parallel": true, "self": 0.00039308000032178825, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011982839996562689, "count": 8, "is_parallel": true, "self": 0.0011982839996562689 } } } } } } }, "UnityEnvironment.step": { "total": 1176.9956625810796, "count": 63591, "is_parallel": true, "self": 31.433264952083846, "children": { "UnityEnvironment._generate_step_input": { "total": 23.105595928984712, "count": 63591, "is_parallel": true, "self": 23.105595928984712 }, "communicator.exchange": { "total": 1028.5575264180552, "count": 63591, "is_parallel": true, "self": 1028.5575264180552 }, "steps_from_proto": { "total": 93.89927528195585, "count": 63591, "is_parallel": true, "self": 18.677189549945524, "children": { "_process_rank_one_or_two_observation": { "total": 75.22208573201033, "count": 508728, "is_parallel": true, "self": 75.22208573201033 } } } } } } } } } } }, "trainer_advance": { "total": 641.5766271950365, "count": 63592, "self": 2.336274466064424, "children": { "process_trajectory": { "total": 123.58145582197221, "count": 63592, "self": 123.39350980897234, "children": { "RLTrainer._checkpoint": { "total": 0.18794601299987335, "count": 2, "self": 0.18794601299987335 } } }, "_update_policy": { "total": 515.6588969069999, "count": 441, "self": 287.99666764094854, "children": { "TorchPPOOptimizer.update": { "total": 227.66222926605133, "count": 22833, "self": 227.66222926605133 } } } } } } }, "trainer_threads": { "total": 1.1170004654559307e-06, "count": 1, "self": 1.1170004654559307e-06 }, "TrainerController._save_models": { "total": 0.07641491899994435, "count": 1, "self": 0.0013094429996272083, "children": { "RLTrainer._checkpoint": { "total": 0.07510547600031714, "count": 1, "self": 0.07510547600031714 } } } } } } }