{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.42486220598220825, "min": 0.42486220598220825, "max": 1.4309312105178833, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12834.2373046875, "min": 12831.9375, "max": 43408.73046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989912.0, "min": 29877.0, "max": 989912.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989912.0, "min": 29877.0, "max": 989912.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.451068252325058, "min": -0.1029493436217308, "max": 0.451068252325058, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 121.33735656738281, "min": -24.707841873168945, "max": 121.33735656738281, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.7124933004379272, "min": -0.34160175919532776, "max": 0.8309169411659241, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 191.66070556640625, "min": -91.89087677001953, "max": 220.1929931640625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07071520843393435, "min": 0.06432107533825528, "max": 0.07478312403733939, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.990012918075081, "min": 0.5121523482603256, "max": 1.0512695443370226, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.03871239505228697, "min": 0.00019125562703348344, "max": 0.0628469823432776, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.5419735307320176, "min": 0.002486323151435285, "max": 0.9427047351491639, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.401076104435714e-06, "min": 7.401076104435714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010361506546209999, "min": 0.00010361506546209999, "max": 0.0036321430892857, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246699285714286, "min": 0.10246699285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345379, "min": 1.3886848, "max": 2.6107143000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025645258642857145, "min": 0.00025645258642857145, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035903362100000004, "min": 0.0035903362100000004, "max": 0.12109035857, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007531429640948772, "min": 0.007386945188045502, "max": 0.49808263778686523, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10544001311063766, "min": 0.10341723263263702, "max": 3.4865784645080566, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 390.6233766233766, "min": 390.6233766233766, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30078.0, "min": 16804.0, "max": 33219.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4794545161066117, "min": -0.9998968270036482, "max": 1.512406126810954, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 113.9179977402091, "min": -30.996801637113094, "max": 113.9179977402091, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4794545161066117, "min": -0.9998968270036482, "max": 1.512406126810954, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 113.9179977402091, "min": -30.996801637113094, "max": 113.9179977402091, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03054239382807093, "min": 0.03054239382807093, "max": 9.510421185809022, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.3517643247614615, "min": 2.169728481421771, "max": 161.6771601587534, "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": "1767311752", "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": "1767313894" }, "total": 2142.542534064, "count": 1, "self": 0.5265964889995303, "children": { "run_training.setup": { "total": 0.022325139000258787, "count": 1, "self": 0.022325139000258787 }, "TrainerController.start_learning": { "total": 2141.993612436, "count": 1, "self": 1.3688219079954251, "children": { "TrainerController._reset_env": { "total": 2.0149411520001195, "count": 1, "self": 2.0149411520001195 }, "TrainerController.advance": { "total": 2138.536226465005, "count": 63678, "self": 1.4289468850120102, "children": { "env_step": { "total": 1488.9654037080195, "count": 63678, "self": 1339.690950546989, "children": { "SubprocessEnvManager._take_step": { "total": 148.47761128004095, "count": 63678, "self": 4.8599120260146265, "children": { "TorchPolicy.evaluate": { "total": 143.61769925402632, "count": 62562, "self": 143.61769925402632 } } }, "workers": { "total": 0.796841880989632, "count": 63678, "self": 0.0, "children": { "worker_root": { "total": 2135.203987172038, "count": 63678, "is_parallel": true, "self": 913.2893998751119, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021233490001577593, "count": 1, "is_parallel": true, "self": 0.0006720060005136475, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014513429996441118, "count": 8, "is_parallel": true, "self": 0.0014513429996441118 } } }, "UnityEnvironment.step": { "total": 0.04804428599982202, "count": 1, "is_parallel": true, "self": 0.000543846999789821, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005332040000212146, "count": 1, "is_parallel": true, "self": 0.0005332040000212146 }, "communicator.exchange": { "total": 0.04526171800034717, "count": 1, "is_parallel": true, "self": 0.04526171800034717 }, "steps_from_proto": { "total": 0.0017055169996638142, "count": 1, "is_parallel": true, "self": 0.0003490120011520048, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013565049985118094, "count": 8, "is_parallel": true, "self": 0.0013565049985118094 } } } } } } }, "UnityEnvironment.step": { "total": 1221.9145872969261, "count": 63677, "is_parallel": true, "self": 34.110541894843664, "children": { "UnityEnvironment._generate_step_input": { "total": 24.002419139062567, "count": 63677, "is_parallel": true, "self": 24.002419139062567 }, "communicator.exchange": { "total": 1052.9913183720219, "count": 63677, "is_parallel": true, "self": 1052.9913183720219 }, "steps_from_proto": { "total": 110.81030789099805, "count": 63677, "is_parallel": true, "self": 23.135755972989955, "children": { "_process_rank_one_or_two_observation": { "total": 87.67455191800809, "count": 509416, "is_parallel": true, "self": 87.67455191800809 } } } } } } } } } } }, "trainer_advance": { "total": 648.1418758719733, "count": 63678, "self": 2.6257939398492454, "children": { "process_trajectory": { "total": 124.04663812612034, "count": 63678, "self": 123.86874062912011, "children": { "RLTrainer._checkpoint": { "total": 0.17789749700023094, "count": 2, "self": 0.17789749700023094 } } }, "_update_policy": { "total": 521.4694438060037, "count": 453, "self": 291.7972398660504, "children": { "TorchPPOOptimizer.update": { "total": 229.6722039399533, "count": 22767, "self": 229.6722039399533 } } } } } } }, "trainer_threads": { "total": 9.85000042419415e-07, "count": 1, "self": 9.85000042419415e-07 }, "TrainerController._save_models": { "total": 0.0736219259997597, "count": 1, "self": 0.0008982149993244093, "children": { "RLTrainer._checkpoint": { "total": 0.07272371100043529, "count": 1, "self": 0.07272371100043529 } } } } } } }