{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4688999354839325, "min": 0.4688999354839325, "max": 1.0806628465652466, "count": 72 }, "Pyramids.Policy.Entropy.sum": { "value": 4508.94189453125, "min": 4246.259765625, "max": 14039.7783203125, "count": 72 }, "Pyramids.Step.mean": { "value": 769971.0, "min": 59925.0, "max": 769971.0, "count": 72 }, "Pyramids.Step.sum": { "value": 769971.0, "min": 59925.0, "max": 769971.0, "count": 72 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8635096549987793, "min": -0.1376415193080902, "max": 0.9315389394760132, "count": 72 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 45.76601028442383, "min": -5.6433024406433105, "max": 52.16617965698242, "count": 72 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.1664518266916275, "min": 0.1583787351846695, "max": 2.521510124206543, "count": 72 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.82194709777832, "min": 7.95475959777832, "max": 101.09890747070312, "count": 72 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 72 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 72 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 383.2142857142857, "min": 263.0967741935484, "max": 999.0, "count": 70 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 10730.0, "min": 1563.0, "max": 16249.0, "count": 70 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.555793086002613, "min": -1.0000000596046448, "max": 1.7420999805132549, "count": 71 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 45.117999494075775, "min": -13.000000774860382, "max": 55.895999640226364, "count": 71 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.555793086002613, "min": -1.0000000596046448, "max": 1.7420999805132549, "count": 71 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 45.117999494075775, "min": -13.000000774860382, "max": 55.895999640226364, "count": 71 }, "Pyramids.Policy.RndReward.mean": { "value": 0.33733158854061157, "min": 0.24494842488008242, "max": 6.90849560040694, "count": 71 }, "Pyramids.Policy.RndReward.sum": { "value": 9.782616067677736, "min": 7.348452746402472, "max": 89.81044280529022, "count": 71 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0448894008969594, "min": 0.038729007850633934, "max": 0.05835424439067504, "count": 71 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.0897788017939188, "min": 0.07745801570126787, "max": 0.16152152708207343, "count": 71 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010544015298875277, "min": 0.0011576393076362084, "max": 0.015580499068806496, "count": 71 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.021088030597750555, "min": 0.002315278615272417, "max": 0.04583625769352212, "count": 71 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00014209537631744998, "min": 0.00014209537631744998, "max": 0.0005618940063509999, "count": 71 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00028419075263489996, "min": 0.00028419075263489996, "max": 0.0016112232314627996, "count": 71 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.12368255000000002, "min": 0.12368255000000002, "max": 0.19364900000000002, "count": 71 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.24736510000000003, "min": 0.24736510000000003, "max": 0.5685372, "count": 71 }, "Pyramids.Policy.Beta.mean": { "value": 0.0023758867450000007, "min": 0.0023758867450000007, "max": 0.009365535099999999, "count": 71 }, "Pyramids.Policy.Beta.sum": { "value": 0.0047517734900000014, "min": 0.0047517734900000014, "max": 0.02685686628, "count": 71 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.017562301829457283, "min": 0.017562301829457283, "max": 0.13998644053936005, "count": 71 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.035124603658914566, "min": 0.035124603658914566, "max": 0.2799728810787201, "count": 71 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1683710513", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/ken/anaconda3/envs/huggingface/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1683711631" }, "total": 1118.4027414129814, "count": 1, "self": 0.0489059139508754, "children": { "run_training.setup": { "total": 0.05294006806798279, "count": 1, "self": 0.05294006806798279 }, "TrainerController.start_learning": { "total": 1118.3008954309626, "count": 1, "self": 2.409382709302008, "children": { "TrainerController._reset_env": { "total": 4.542555338935927, "count": 1, "self": 4.542555338935927 }, "TrainerController.advance": { "total": 1111.0216540957335, "count": 45677, "self": 0.6503811537986621, "children": { "env_step": { "total": 1110.3712729419349, "count": 45677, "self": 1035.2698940025875, "children": { "SubprocessEnvManager._take_step": { "total": 74.4824052240001, "count": 45677, "self": 3.166508529218845, "children": { "TorchPolicy.evaluate": { "total": 71.31589669478126, "count": 44716, "self": 71.31589669478126 } } }, "workers": { "total": 0.6189737153472379, "count": 45676, "self": 0.0, "children": { "worker_root": { "total": 1115.688862252864, "count": 45676, "is_parallel": true, "self": 408.390744590899, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020214449614286423, "count": 1, "is_parallel": true, "self": 0.000529911951161921, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014915330102667212, "count": 8, "is_parallel": true, "self": 0.0014915330102667212 } } }, "UnityEnvironment.step": { "total": 0.030255171936005354, "count": 1, "is_parallel": true, "self": 0.0002020038664340973, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020190502982586622, "count": 1, "is_parallel": true, "self": 0.00020190502982586622 }, "communicator.exchange": { "total": 0.029121847008354962, "count": 1, "is_parallel": true, "self": 0.029121847008354962 }, "steps_from_proto": { "total": 0.0007294160313904285, "count": 1, "is_parallel": true, "self": 0.00024750595912337303, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004819100722670555, "count": 8, "is_parallel": true, "self": 0.0004819100722670555 } } } } } } }, "UnityEnvironment.step": { "total": 707.2981176619651, "count": 45675, "is_parallel": true, "self": 11.123494700877927, "children": { "UnityEnvironment._generate_step_input": { "total": 9.179199861944653, "count": 45675, "is_parallel": true, "self": 9.179199861944653 }, "communicator.exchange": { "total": 653.2296731449896, "count": 45675, "is_parallel": true, "self": 653.2296731449896 }, "steps_from_proto": { "total": 33.76574995415285, "count": 45675, "is_parallel": true, "self": 8.269278136780486, "children": { "_process_rank_one_or_two_observation": { "total": 25.496471817372367, "count": 365400, "is_parallel": true, "self": 25.496471817372367 } } } } } } } } } } } } }, "trainer_threads": { "total": 5.560100544244051e-05, "count": 1, "self": 5.560100544244051e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1110.651754460414, "count": 18512, "is_parallel": true, "self": 0.09175604523625225, "children": { "process_trajectory": { "total": 233.9755890709348, "count": 18513, "is_parallel": true, "self": 233.43589032802265, "children": { "RLTrainer._checkpoint": { "total": 0.5396987429121509, "count": 1, "is_parallel": true, "self": 0.5396987429121509 } } }, "_update_policy": { "total": 876.5844093442429, "count": 152, "is_parallel": true, "self": 514.0643083131872, "children": { "TorchPPOOptimizer.update": { "total": 362.5201010310557, "count": 8091, "is_parallel": true, "self": 362.5201010310557 } } } } } } } } }, "TrainerController._save_models": { "total": 0.3272476859856397, "count": 1, "self": 0.11190811998676509, "children": { "RLTrainer._checkpoint": { "total": 0.2153395659988746, "count": 1, "self": 0.2153395659988746 } } } } } } }