{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5397613644599915, "min": 0.5057464838027954, "max": 1.5166629552841187, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16063.298828125, "min": 15253.314453125, "max": 46009.48828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989891.0, "min": 29952.0, "max": 989891.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989891.0, "min": 29952.0, "max": 989891.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.009143930859863758, "min": -0.10815303772687912, "max": 0.09564892202615738, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 2.2036874294281006, "min": -25.956729888916016, "max": 24.00787925720215, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.034235402941703796, "min": 0.0029469288419932127, "max": 0.2943683862686157, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.250732421875, "min": 0.7190506458282471, "max": 69.76530456542969, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0678609770103762, "min": 0.06314270149736897, "max": 0.07373202628400471, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9500536781452669, "min": 0.5067776090023243, "max": 1.038052537148663, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00397560266647823, "min": 9.786778065576939e-05, "max": 0.013331007585006525, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.05565843733069522, "min": 0.0011744133678692327, "max": 0.09331705309504568, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.290697569799999e-06, "min": 7.290697569799999e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010206976597719999, "min": 0.00010206976597719999, "max": 0.0031169593610136, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024302, "min": 0.1024302, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340228, "min": 1.3886848, "max": 2.4004653000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025277698, "min": 0.00025277698, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035388777200000003, "min": 0.0035388777200000003, "max": 0.10391474136000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010025358758866787, "min": 0.010025358758866787, "max": 0.3218231797218323, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14035502076148987, "min": 0.14035502076148987, "max": 2.2527623176574707, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 887.6176470588235, "min": 760.4285714285714, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30179.0, "min": 15984.0, "max": 33785.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.41745298750260296, "min": -1.0000000521540642, "max": 0.39909264572509906, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -14.193401575088501, "min": -31.998801678419113, "max": 16.36279847472906, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.41745298750260296, "min": -1.0000000521540642, "max": 0.39909264572509906, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -14.193401575088501, "min": -31.998801678419113, "max": 16.36279847472906, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.09184312147280092, "min": 0.08400345196423586, "max": 7.227232546545565, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.122666130075231, "min": 2.8810590205248445, "max": 115.63572074472904, "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": "1785335178", "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=PyramidsTraining_v2 --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": "1785337484" }, "total": 2305.431075845, "count": 1, "self": 0.48129190300096525, "children": { "run_training.setup": { "total": 0.025843038999482815, "count": 1, "self": 0.025843038999482815 }, "TrainerController.start_learning": { "total": 2304.9239409029997, "count": 1, "self": 1.396206116049143, "children": { "TrainerController._reset_env": { "total": 2.1838399649996063, "count": 1, "self": 2.1838399649996063 }, "TrainerController.advance": { "total": 2301.1791481419505, "count": 63229, "self": 1.3696344049849358, "children": { "env_step": { "total": 1672.1050102719983, "count": 63229, "self": 1518.2094805428424, "children": { "SubprocessEnvManager._take_step": { "total": 153.09258657726969, "count": 63229, "self": 4.6154354161280935, "children": { "TorchPolicy.evaluate": { "total": 148.4771511611416, "count": 62561, "self": 148.4771511611416 } } }, "workers": { "total": 0.8029431518862111, "count": 63229, "self": 0.0, "children": { "worker_root": { "total": 2298.6389207259635, "count": 63229, "is_parallel": true, "self": 898.5448377729117, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017264820007767412, "count": 1, "is_parallel": true, "self": 0.0005974480000077165, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011290340007690247, "count": 8, "is_parallel": true, "self": 0.0011290340007690247 } } }, "UnityEnvironment.step": { "total": 0.052750169999853824, "count": 1, "is_parallel": true, "self": 0.000541356000212545, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005445770002552308, "count": 1, "is_parallel": true, "self": 0.0005445770002552308 }, "communicator.exchange": { "total": 0.05001094399995054, "count": 1, "is_parallel": true, "self": 0.05001094399995054 }, "steps_from_proto": { "total": 0.0016532929994355072, "count": 1, "is_parallel": true, "self": 0.00037035500008641975, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012829379993490875, "count": 8, "is_parallel": true, "self": 0.0012829379993490875 } } } } } } }, "UnityEnvironment.step": { "total": 1400.0940829530518, "count": 63228, "is_parallel": true, "self": 34.1250701400586, "children": { "UnityEnvironment._generate_step_input": { "total": 23.780719299981683, "count": 63228, "is_parallel": true, "self": 23.780719299981683 }, "communicator.exchange": { "total": 1233.4198023560275, "count": 63228, "is_parallel": true, "self": 1233.4198023560275 }, "steps_from_proto": { "total": 108.76849115698406, "count": 63228, "is_parallel": true, "self": 22.44260716572171, "children": { "_process_rank_one_or_two_observation": { "total": 86.32588399126234, "count": 505824, "is_parallel": true, "self": 86.32588399126234 } } } } } } } } } } }, "trainer_advance": { "total": 627.7045034649673, "count": 63229, "self": 2.480343906827329, "children": { "process_trajectory": { "total": 107.04456401713378, "count": 63229, "self": 106.70531108913292, "children": { "RLTrainer._checkpoint": { "total": 0.33925292800086027, "count": 2, "self": 0.33925292800086027 } } }, "_update_policy": { "total": 518.1795955410062, "count": 438, "self": 272.1952725569563, "children": { "TorchPPOOptimizer.update": { "total": 245.98432298404987, "count": 22767, "self": 245.98432298404987 } } } } } } }, "trainer_threads": { "total": 1.1310003174003214e-06, "count": 1, "self": 1.1310003174003214e-06 }, "TrainerController._save_models": { "total": 0.16474554900014482, "count": 1, "self": 0.0025564030001987703, "children": { "RLTrainer._checkpoint": { "total": 0.16218914599994605, "count": 1, "self": 0.16218914599994605 } } } } } } }