{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.16909362375736237, "min": 0.1535557508468628, "max": 1.4912805557250977, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5091.7470703125, "min": 4591.93115234375, "max": 45239.48828125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999921.0, "min": 29952.0, "max": 2999921.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999921.0, "min": 29952.0, "max": 2999921.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.698056161403656, "min": -0.0990222617983818, "max": 0.8492839336395264, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 205.228515625, "min": -23.765342712402344, "max": 257.9645690917969, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.004896752070635557, "min": -0.07059083133935928, "max": 0.2797944247722626, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.4396451711654663, "min": -17.506526947021484, "max": 67.43045806884766, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06634856978218079, "min": 0.06398052713623094, "max": 0.07496232472536063, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.928879976950531, "min": 0.4891745000726399, "max": 1.084693093572152, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01419425931173352, "min": 0.0001452797957554366, "max": 0.015902644161704102, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1987196303642693, "min": 0.0018886373448206758, "max": 0.23853966242556154, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.454578086602381e-06, "min": 1.454578086602381e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0364093212433334e-05, "min": 2.0364093212433334e-05, "max": 0.003892461402512933, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1004848261904762, "min": 0.1004848261904762, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.406787566666667, "min": 1.3962282666666668, "max": 2.7974870666666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.8434136428571426e-05, "min": 5.8434136428571426e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.00081807791, "min": 0.00081807791, "max": 0.12976895796, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.003929897211492062, "min": 0.0038511455059051514, "max": 0.34112435579299927, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.05501855909824371, "min": 0.05391603708267212, "max": 2.3878705501556396, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 266.9491525423729, "min": 220.09923664122138, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31500.0, "min": 15984.0, "max": 34463.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6652237175000926, "min": -1.0000000521540642, "max": 1.7799007447848794, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 196.49639866501093, "min": -31.998401656746864, "max": 241.6267975270748, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6652237175000926, "min": -1.0000000521540642, "max": 1.7799007447848794, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 196.49639866501093, "min": -31.998401656746864, "max": 241.6267975270748, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.010968116473754813, "min": 0.009014557689790747, "max": 6.435719049535692, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.294237743903068, "min": 1.1519952498347266, "max": 102.97150479257107, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1751557382", "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": "1751564595" }, "total": 7213.020300012, "count": 1, "self": 0.49145585799942637, "children": { "run_training.setup": { "total": 0.022117432000072768, "count": 1, "self": 0.022117432000072768 }, "TrainerController.start_learning": { "total": 7212.506726722, "count": 1, "self": 4.087200834875148, "children": { "TrainerController._reset_env": { "total": 3.3827620170000046, "count": 1, "self": 3.3827620170000046 }, "TrainerController.advance": { "total": 7204.950937205124, "count": 195091, "self": 4.339133555014087, "children": { "env_step": { "total": 5220.561583499158, "count": 195091, "self": 4777.050485230879, "children": { "SubprocessEnvManager._take_step": { "total": 441.0496302792393, "count": 195091, "self": 13.650393263460387, "children": { "TorchPolicy.evaluate": { "total": 427.3992370157789, "count": 187563, "self": 427.3992370157789 } } }, "workers": { "total": 2.4614679890393063, "count": 195091, "self": 0.0, "children": { "worker_root": { "total": 7196.235912937945, "count": 195091, "is_parallel": true, "self": 2763.507359051886, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004882540000039626, "count": 1, "is_parallel": true, "self": 0.0036236399997733315, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012589000002662942, "count": 8, "is_parallel": true, "self": 0.0012589000002662942 } } }, "UnityEnvironment.step": { "total": 0.07241658199995982, "count": 1, "is_parallel": true, "self": 0.0005710699998644486, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047171500000331434, "count": 1, "is_parallel": true, "self": 0.00047171500000331434 }, "communicator.exchange": { "total": 0.06973621800000274, "count": 1, "is_parallel": true, "self": 0.06973621800000274 }, "steps_from_proto": { "total": 0.0016375790000893176, "count": 1, "is_parallel": true, "self": 0.00034563600002002204, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012919430000692955, "count": 8, "is_parallel": true, "self": 0.0012919430000692955 } } } } } } }, "UnityEnvironment.step": { "total": 4432.728553886059, "count": 195090, "is_parallel": true, "self": 98.31464736939961, "children": { "UnityEnvironment._generate_step_input": { "total": 68.5793789248986, "count": 195090, "is_parallel": true, "self": 68.5793789248986 }, "communicator.exchange": { "total": 3974.551952471862, "count": 195090, "is_parallel": true, "self": 3974.551952471862 }, "steps_from_proto": { "total": 291.2825751198985, "count": 195090, "is_parallel": true, "self": 59.070041295795136, "children": { "_process_rank_one_or_two_observation": { "total": 232.2125338241034, "count": 1560720, "is_parallel": true, "self": 232.2125338241034 } } } } } } } } } } }, "trainer_advance": { "total": 1980.0502201509526, "count": 195091, "self": 8.350221393136508, "children": { "process_trajectory": { "total": 389.788887078839, "count": 195091, "self": 389.0900546088392, "children": { "RLTrainer._checkpoint": { "total": 0.6988324699998429, "count": 6, "self": 0.6988324699998429 } } }, "_update_policy": { "total": 1581.911111678977, "count": 1389, "self": 882.1051162249698, "children": { "TorchPPOOptimizer.update": { "total": 699.8059954540072, "count": 68397, "self": 699.8059954540072 } } } } } } }, "trainer_threads": { "total": 1.0140001904801466e-06, "count": 1, "self": 1.0140001904801466e-06 }, "TrainerController._save_models": { "total": 0.08582565100005013, "count": 1, "self": 0.0013370790002227295, "children": { "RLTrainer._checkpoint": { "total": 0.0844885719998274, "count": 1, "self": 0.0844885719998274 } } } } } } }