{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5155686736106873, "min": 0.5128698945045471, "max": 1.480726718902588, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15343.32421875, "min": 15343.32421875, "max": 44919.32421875, "count": 33 }, "Pyramids.Step.mean": { "value": 989928.0, "min": 29940.0, "max": 989928.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989928.0, "min": 29940.0, "max": 989928.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2655923068523407, "min": -0.0993962213397026, "max": 0.363382488489151, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 68.78840637207031, "min": -23.556903839111328, "max": 96.65974426269531, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -1.3531920909881592, "min": -1.3531920909881592, "max": 0.4172818064689636, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -350.47674560546875, "min": -350.47674560546875, "max": 110.99696350097656, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06800666713942995, "min": 0.06348549001060226, "max": 0.07338918411350322, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9520933399520193, "min": 0.5047890518088798, "max": 1.0706449622036112, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.3558263771812476, "min": 0.00020599436135512432, "max": 0.3558263771812476, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 4.9815692805374665, "min": 0.002677926697616616, "max": 4.9815692805374665, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.345040408828575e-06, "min": 7.345040408828575e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010283056572360005, "min": 0.00010283056572360005, "max": 0.003508346030551399, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244831428571431, "min": 0.10244831428571431, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342764000000003, "min": 1.3886848, "max": 2.5694486000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002545865971428573, "min": 0.0002545865971428573, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035642123600000022, "min": 0.0035642123600000022, "max": 0.11696791514, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010971345007419586, "min": 0.01027912087738514, "max": 0.4431288242340088, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1535988301038742, "min": 0.1498798429965973, "max": 3.1019017696380615, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 543.574074074074, "min": 452.46153846153845, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29353.0, "min": 16867.0, "max": 32542.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.0859444124831095, "min": -0.9999936006722911, "max": 1.3936461298511578, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 58.640998274087906, "min": -31.998401656746864, "max": 90.58699844032526, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.0859444124831095, "min": -0.9999936006722911, "max": 1.3936461298511578, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 58.640998274087906, "min": -31.998401656746864, "max": 90.58699844032526, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06160674647091784, "min": 0.05156582837651233, "max": 9.068151594084853, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3267643094295636, "min": 3.111286702682264, "max": 154.15857709944248, "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": "1681004747", "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 Training --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": "1681006824" }, "total": 2077.360403674, "count": 1, "self": 0.483012795999457, "children": { "run_training.setup": { "total": 0.1141264840000531, "count": 1, "self": 0.1141264840000531 }, "TrainerController.start_learning": { "total": 2076.763264394, "count": 1, "self": 1.368847760889821, "children": { "TrainerController._reset_env": { "total": 3.9053872270000056, "count": 1, "self": 3.9053872270000056 }, "TrainerController.advance": { "total": 2071.39178355411, "count": 63353, "self": 1.4502579250661256, "children": { "env_step": { "total": 1443.406999009006, "count": 63353, "self": 1337.2951103130113, "children": { "SubprocessEnvManager._take_step": { "total": 105.31902369003024, "count": 63353, "self": 4.759278668032948, "children": { "TorchPolicy.evaluate": { "total": 100.55974502199729, "count": 62567, "self": 100.55974502199729 } } }, "workers": { "total": 0.7928650059646998, "count": 63353, "self": 0.0, "children": { "worker_root": { "total": 2071.7996064910144, "count": 63353, "is_parallel": true, "self": 844.2455680059734, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017289159999336334, "count": 1, "is_parallel": true, "self": 0.0005661100000224906, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011628059999111429, "count": 8, "is_parallel": true, "self": 0.0011628059999111429 } } }, "UnityEnvironment.step": { "total": 0.05158070300001327, "count": 1, "is_parallel": true, "self": 0.0013342060000240963, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005451399999856221, "count": 1, "is_parallel": true, "self": 0.0005451399999856221 }, "communicator.exchange": { "total": 0.048098138999989715, "count": 1, "is_parallel": true, "self": 0.048098138999989715 }, "steps_from_proto": { "total": 0.0016032180000138396, "count": 1, "is_parallel": true, "self": 0.00037989500003732246, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012233229999765172, "count": 8, "is_parallel": true, "self": 0.0012233229999765172 } } } } } } }, "UnityEnvironment.step": { "total": 1227.554038485041, "count": 63352, "is_parallel": true, "self": 32.942668925014914, "children": { "UnityEnvironment._generate_step_input": { "total": 23.574204810056244, "count": 63352, "is_parallel": true, "self": 23.574204810056244 }, "communicator.exchange": { "total": 1075.9845709729962, "count": 63352, "is_parallel": true, "self": 1075.9845709729962 }, "steps_from_proto": { "total": 95.05259377697382, "count": 63352, "is_parallel": true, "self": 19.70514538996747, "children": { "_process_rank_one_or_two_observation": { "total": 75.34744838700635, "count": 506816, "is_parallel": true, "self": 75.34744838700635 } } } } } } } } } } }, "trainer_advance": { "total": 626.5345266200377, "count": 63353, "self": 2.5457139629531866, "children": { "process_trajectory": { "total": 104.43931524008565, "count": 63353, "self": 104.22606468308561, "children": { "RLTrainer._checkpoint": { "total": 0.2132505570000376, "count": 2, "self": 0.2132505570000376 } } }, "_update_policy": { "total": 519.5494974169989, "count": 449, "self": 332.6558949279877, "children": { "TorchPPOOptimizer.update": { "total": 186.8936024890112, "count": 22821, "self": 186.8936024890112 } } } } } } }, "trainer_threads": { "total": 9.830000635702163e-07, "count": 1, "self": 9.830000635702163e-07 }, "TrainerController._save_models": { "total": 0.097244868999951, "count": 1, "self": 0.0014881339998282783, "children": { "RLTrainer._checkpoint": { "total": 0.09575673500012272, "count": 1, "self": 0.09575673500012272 } } } } } } }