{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6303697824478149, "min": 0.6303697824478149, "max": 1.5210086107254028, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18981.6953125, "min": 18981.6953125, "max": 46141.31640625, "count": 33 }, "Pyramids.Step.mean": { "value": 989995.0, "min": 29952.0, "max": 989995.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989995.0, "min": 29952.0, "max": 989995.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.14960183203220367, "min": -0.1330912858247757, "max": 0.1675247848033905, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 37.5500602722168, "min": -31.941909790039062, "max": 42.04872131347656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.3084894120693207, "min": -0.012797262519598007, "max": 0.3084894120693207, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 77.43083953857422, "min": -3.186518430709839, "max": 77.43083953857422, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07028482531468679, "min": 0.06558102516551842, "max": 0.07462744320190383, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.983987554405615, "min": 0.4781911771056368, "max": 1.0447842048266536, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.02289279433680553, "min": 0.0004112417452750099, "max": 0.02289279433680553, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.3204991207152774, "min": 0.005757384433850139, "max": 0.3204991207152774, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.3560332623071444e-06, "min": 7.3560332623071444e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010298446567230003, "min": 0.00010298446567230003, "max": 0.0032598599133801, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245197857142858, "min": 0.10245197857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343277, "min": 1.3886848, "max": 2.4849295000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025495265928571437, "min": 0.00025495265928571437, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003569337230000001, "min": 0.003569337230000001, "max": 0.10868332801, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01016259752213955, "min": 0.01016259752213955, "max": 0.2812757194042206, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1422763615846634, "min": 0.1422763615846634, "max": 1.9689300060272217, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 768.65, "min": 638.2444444444444, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30746.0, "min": 15984.0, "max": 32864.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.3311649657785892, "min": -1.0000000521540642, "max": 0.650417740146319, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 13.24659863114357, "min": -31.998801678419113, "max": 29.268798306584358, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.3311649657785892, "min": -1.0000000521540642, "max": 0.650417740146319, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 13.24659863114357, "min": -31.998801678419113, "max": 29.268798306584358, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08200378341862233, "min": 0.07021325422554381, "max": 5.856541678309441, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2801513367448933, "min": 2.860849268938182, "max": 93.70466685295105, "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": "1690548537", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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 --force", "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": "1690550707" }, "total": 2170.0347790650003, "count": 1, "self": 0.5273945090002599, "children": { "run_training.setup": { "total": 0.032459447000064756, "count": 1, "self": 0.032459447000064756 }, "TrainerController.start_learning": { "total": 2169.4749251089997, "count": 1, "self": 1.4418142929912392, "children": { "TrainerController._reset_env": { "total": 5.0535824800000455, "count": 1, "self": 5.0535824800000455 }, "TrainerController.advance": { "total": 2162.8779374340083, "count": 63253, "self": 1.424417580986301, "children": { "env_step": { "total": 1476.2941121030408, "count": 63253, "self": 1363.4744240089476, "children": { "SubprocessEnvManager._take_step": { "total": 111.96958134102306, "count": 63253, "self": 4.88128843000095, "children": { "TorchPolicy.evaluate": { "total": 107.08829291102211, "count": 62567, "self": 107.08829291102211 } } }, "workers": { "total": 0.8501067530700084, "count": 63253, "self": 0.0, "children": { "worker_root": { "total": 2164.5678910580195, "count": 63253, "is_parallel": true, "self": 917.1905538309647, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017091740000978461, "count": 1, "is_parallel": true, "self": 0.00053114600018489, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011780279999129561, "count": 8, "is_parallel": true, "self": 0.0011780279999129561 } } }, "UnityEnvironment.step": { "total": 0.08470730299995921, "count": 1, "is_parallel": true, "self": 0.0006570800001099997, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047147199995833944, "count": 1, "is_parallel": true, "self": 0.00047147199995833944 }, "communicator.exchange": { "total": 0.081549177999932, "count": 1, "is_parallel": true, "self": 0.081549177999932 }, "steps_from_proto": { "total": 0.002029572999958873, "count": 1, "is_parallel": true, "self": 0.00038762199983466417, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016419510001242088, "count": 8, "is_parallel": true, "self": 0.0016419510001242088 } } } } } } }, "UnityEnvironment.step": { "total": 1247.3773372270548, "count": 63252, "is_parallel": true, "self": 35.08602395205753, "children": { "UnityEnvironment._generate_step_input": { "total": 23.42467414399357, "count": 63252, "is_parallel": true, "self": 23.42467414399357 }, "communicator.exchange": { "total": 1084.145793347045, "count": 63252, "is_parallel": true, "self": 1084.145793347045 }, "steps_from_proto": { "total": 104.7208457839588, "count": 63252, "is_parallel": true, "self": 21.23839937698665, "children": { "_process_rank_one_or_two_observation": { "total": 83.48244640697214, "count": 506016, "is_parallel": true, "self": 83.48244640697214 } } } } } } } } } } }, "trainer_advance": { "total": 685.1594077499813, "count": 63253, "self": 2.6217041779806323, "children": { "process_trajectory": { "total": 110.93536910999421, "count": 63253, "self": 110.71558891299458, "children": { "RLTrainer._checkpoint": { "total": 0.21978019699963625, "count": 2, "self": 0.21978019699963625 } } }, "_update_policy": { "total": 571.6023344620064, "count": 446, "self": 373.98363804293103, "children": { "TorchPPOOptimizer.update": { "total": 197.61869641907538, "count": 22800, "self": 197.61869641907538 } } } } } } }, "trainer_threads": { "total": 9.919999683916103e-07, "count": 1, "self": 9.919999683916103e-07 }, "TrainerController._save_models": { "total": 0.10158991000025708, "count": 1, "self": 0.001403854000272986, "children": { "RLTrainer._checkpoint": { "total": 0.10018605599998409, "count": 1, "self": 0.10018605599998409 } } } } } } }