{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.19362211227416992, "min": 0.1847541183233261, "max": 1.45942223072052, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5796.271484375, "min": 5489.41455078125, "max": 44273.03125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999979.0, "min": 29952.0, "max": 2999979.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999979.0, "min": 29952.0, "max": 2999979.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.791162371635437, "min": -0.10061295330524445, "max": 0.8743876814842224, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 240.51336669921875, "min": -24.247722625732422, "max": 268.43701171875, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.017733510583639145, "min": -0.017733510583639145, "max": 0.22232423722743988, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -5.390987396240234, "min": -5.390987396240234, "max": 53.357818603515625, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06508579826051439, "min": 0.06383762338482495, "max": 0.07451985432325377, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9112011756472014, "min": 0.4836785304361764, "max": 1.0635239851590264, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015127839972375936, "min": 1.5796632388096363e-05, "max": 0.016879084691730085, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2117897596132631, "min": 0.00022115285343334907, "max": 0.2399299976441041, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.489606646354762e-06, "min": 1.489606646354762e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.085449304896667e-05, "min": 2.085449304896667e-05, "max": 0.003800954133015333, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1004965023809524, "min": 0.1004965023809524, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4069510333333335, "min": 1.3757013333333334, "max": 2.666984666666666, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.960058785714285e-05, "min": 5.960058785714285e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.00083440823, "min": 0.00083440823, "max": 0.1267117682, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005429855082184076, "min": 0.005429855082184076, "max": 0.3427159786224365, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07601796835660934, "min": 0.07601796835660934, "max": 2.3990118503570557, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 229.23134328358208, "min": 196.72972972972974, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30717.0, "min": 15984.0, "max": 32617.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7558402844996595, "min": -1.0000000521540642, "max": 1.8032702628422428, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 235.28259812295437, "min": -32.000001668930054, "max": 266.88399890065193, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7558402844996595, "min": -1.0000000521540642, "max": 1.8032702628422428, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 235.28259812295437, "min": -32.000001668930054, "max": 266.88399890065193, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.012949485503376403, "min": 0.011265934898138102, "max": 6.474831345491111, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.735231057452438, "min": 1.64298190343834, "max": 103.59730152785778, "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": "1713351882", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713361091" }, "total": 9209.762512049, "count": 1, "self": 0.5290154329995858, "children": { "run_training.setup": { "total": 0.06038557900001251, "count": 1, "self": 0.06038557900001251 }, "TrainerController.start_learning": { "total": 9209.173111037, "count": 1, "self": 6.772000372018738, "children": { "TrainerController._reset_env": { "total": 2.4232215900001393, "count": 1, "self": 2.4232215900001393 }, "TrainerController.advance": { "total": 9199.87296700698, "count": 194243, "self": 7.537687351974455, "children": { "env_step": { "total": 6916.275380983646, "count": 194243, "self": 6349.768033540945, "children": { "SubprocessEnvManager._take_step": { "total": 562.1788579116994, "count": 194243, "self": 19.786448805965165, "children": { "TorchPolicy.evaluate": { "total": 542.3924091057343, "count": 187563, "self": 542.3924091057343 } } }, "workers": { "total": 4.3284895310014235, "count": 194243, "self": 0.0, "children": { "worker_root": { "total": 9187.75996207304, "count": 194243, "is_parallel": true, "self": 3373.9576148301185, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002587927000149648, "count": 1, "is_parallel": true, "self": 0.0008261080001830123, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017618189999666356, "count": 8, "is_parallel": true, "self": 0.0017618189999666356 } } }, "UnityEnvironment.step": { "total": 0.059675560999949084, "count": 1, "is_parallel": true, "self": 0.0007619969999268505, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005881670001599559, "count": 1, "is_parallel": true, "self": 0.0005881670001599559 }, "communicator.exchange": { "total": 0.056231754999998884, "count": 1, "is_parallel": true, "self": 0.056231754999998884 }, "steps_from_proto": { "total": 0.0020936419998633937, "count": 1, "is_parallel": true, "self": 0.0004241019998971751, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016695399999662186, "count": 8, "is_parallel": true, "self": 0.0016695399999662186 } } } } } } }, "UnityEnvironment.step": { "total": 5813.802347242921, "count": 194242, "is_parallel": true, "self": 145.47500921213668, "children": { "UnityEnvironment._generate_step_input": { "total": 94.27234482998688, "count": 194242, "is_parallel": true, "self": 94.27234482998688 }, "communicator.exchange": { "total": 5158.305238084848, "count": 194242, "is_parallel": true, "self": 5158.305238084848 }, "steps_from_proto": { "total": 415.7497551159504, "count": 194242, "is_parallel": true, "self": 89.22871351491176, "children": { "_process_rank_one_or_two_observation": { "total": 326.52104160103863, "count": 1553936, "is_parallel": true, "self": 326.52104160103863 } } } } } } } } } } }, "trainer_advance": { "total": 2276.059898671361, "count": 194243, "self": 12.876001527384688, "children": { "process_trajectory": { "total": 491.4855403219674, "count": 194243, "self": 490.80122458697065, "children": { "RLTrainer._checkpoint": { "total": 0.6843157349967441, "count": 6, "self": 0.6843157349967441 } } }, "_update_policy": { "total": 1771.698356822009, "count": 1377, "self": 1041.3567689831357, "children": { "TorchPPOOptimizer.update": { "total": 730.3415878388732, "count": 68448, "self": 730.3415878388732 } } } } } } }, "trainer_threads": { "total": 1.1709998943842947e-06, "count": 1, "self": 1.1709998943842947e-06 }, "TrainerController._save_models": { "total": 0.10492089699982898, "count": 1, "self": 0.0019188860005669994, "children": { "RLTrainer._checkpoint": { "total": 0.10300201099926198, "count": 1, "self": 0.10300201099926198 } } } } } } }