{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.16096897423267365, "min": 0.14876024425029755, "max": 1.4950333833694458, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4795.587890625, "min": 4500.89013671875, "max": 45353.33203125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999920.0, "min": 29952.0, "max": 2999920.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999920.0, "min": 29952.0, "max": 2999920.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7195019125938416, "min": -0.10281172394752502, "max": 0.8429367542266846, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 215.85057067871094, "min": -24.674814224243164, "max": 257.095703125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.000459843227872625, "min": -0.012634320184588432, "max": 0.3526884615421295, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.13795296847820282, "min": -3.436535120010376, "max": 83.58716583251953, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07070109220443381, "min": 0.0641780027986637, "max": 0.07430388593676537, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9898152908620734, "min": 0.49664830050836634, "max": 1.1107229402793262, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016122589864174926, "min": 6.076560459711214e-05, "max": 0.016779721722871597, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22571625809844895, "min": 0.00085071846435957, "max": 0.2393952761485707, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.572149475983335e-06, "min": 1.572149475983335e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.201009266376669e-05, "min": 2.201009266376669e-05, "max": 0.0037601647466117996, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10052401666666667, "min": 0.10052401666666667, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4073362333333335, "min": 1.3962282666666668, "max": 2.6625092333333344, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.234926500000007e-05, "min": 6.234926500000007e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.000872889710000001, "min": 0.000872889710000001, "max": 0.12535348118, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006329101510345936, "min": 0.005974752362817526, "max": 0.4367137849330902, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08860742300748825, "min": 0.08761986345052719, "max": 3.0569965839385986, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 248.725, "min": 213.22058823529412, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29847.0, "min": 15984.0, "max": 32810.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.717931648902595, "min": -1.0000000521540642, "max": 1.7718192444907295, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 206.1517978683114, "min": -31.99920167028904, "max": 239.19559800624847, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.717931648902595, "min": -1.0000000521540642, "max": 1.7718192444907295, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 206.1517978683114, "min": -31.99920167028904, "max": 239.19559800624847, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01639208896758646, "min": 0.014525368729664478, "max": 9.397284805774689, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.9670506761103752, "min": 1.8880921779345954, "max": 150.35655689239502, "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": "1679441539", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids --no-graphics", "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": "1679448402" }, "total": 6862.614617613, "count": 1, "self": 0.5405958100000134, "children": { "run_training.setup": { "total": 0.11967135800000506, "count": 1, "self": 0.11967135800000506 }, "TrainerController.start_learning": { "total": 6861.954350444999, "count": 1, "self": 4.33616354494643, "children": { "TrainerController._reset_env": { "total": 7.462404110999842, "count": 1, "self": 7.462404110999842 }, "TrainerController.advance": { "total": 6850.059569133054, "count": 193679, "self": 4.529224393205368, "children": { "env_step": { "total": 4986.493455598797, "count": 193679, "self": 4665.450209801872, "children": { "SubprocessEnvManager._take_step": { "total": 318.5402583558498, "count": 193679, "self": 14.338749325856725, "children": { "TorchPolicy.evaluate": { "total": 304.2015090299931, "count": 187564, "self": 304.2015090299931 } } }, "workers": { "total": 2.5029874410749926, "count": 193679, "self": 0.0, "children": { "worker_root": { "total": 6847.169389725207, "count": 193679, "is_parallel": true, "self": 2535.8958777763864, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018020020002040837, "count": 1, "is_parallel": true, "self": 0.0005680580002263014, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012339439999777824, "count": 8, "is_parallel": true, "self": 0.0012339439999777824 } } }, "UnityEnvironment.step": { "total": 0.049280583000154365, "count": 1, "is_parallel": true, "self": 0.0005262150000362453, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004740480001146352, "count": 1, "is_parallel": true, "self": 0.0004740480001146352 }, "communicator.exchange": { "total": 0.04656391100002111, "count": 1, "is_parallel": true, "self": 0.04656391100002111 }, "steps_from_proto": { "total": 0.0017164089999823773, "count": 1, "is_parallel": true, "self": 0.0003677890001654305, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013486199998169468, "count": 8, "is_parallel": true, "self": 0.0013486199998169468 } } } } } } }, "UnityEnvironment.step": { "total": 4311.273511948821, "count": 193678, "is_parallel": true, "self": 93.80901501152493, "children": { "UnityEnvironment._generate_step_input": { "total": 68.40516835625385, "count": 193678, "is_parallel": true, "self": 68.40516835625385 }, "communicator.exchange": { "total": 3872.1715493939573, "count": 193678, "is_parallel": true, "self": 3872.1715493939573 }, "steps_from_proto": { "total": 276.88777918708456, "count": 193678, "is_parallel": true, "self": 59.78770844308701, "children": { "_process_rank_one_or_two_observation": { "total": 217.10007074399755, "count": 1549424, "is_parallel": true, "self": 217.10007074399755 } } } } } } } } } } }, "trainer_advance": { "total": 1859.0368891410515, "count": 193679, "self": 8.160331333039494, "children": { "process_trajectory": { "total": 352.3113584860191, "count": 193679, "self": 351.60750803601763, "children": { "RLTrainer._checkpoint": { "total": 0.7038504500014824, "count": 6, "self": 0.7038504500014824 } } }, "_update_policy": { "total": 1498.5651993219928, "count": 1388, "self": 958.2148388050259, "children": { "TorchPPOOptimizer.update": { "total": 540.3503605169669, "count": 68316, "self": 540.3503605169669 } } } } } } }, "trainer_threads": { "total": 9.099985618377104e-07, "count": 1, "self": 9.099985618377104e-07 }, "TrainerController._save_models": { "total": 0.09621274600067409, "count": 1, "self": 0.0014842580021650065, "children": { "RLTrainer._checkpoint": { "total": 0.09472848799850908, "count": 1, "self": 0.09472848799850908 } } } } } } }