{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5299129486083984, "min": 0.5299129486083984, "max": 1.4969733953475952, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15871.953125, "min": 15871.953125, "max": 45412.18359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989923.0, "min": 29952.0, "max": 989923.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989923.0, "min": 29952.0, "max": 989923.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.09612051397562027, "min": -0.10828598588705063, "max": 0.12649278342723846, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 23.837886810302734, "min": -26.096921920776367, "max": 31.876182556152344, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01659237965941429, "min": 0.00712197320535779, "max": 0.2423049360513687, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.114910125732422, "min": 1.7520054578781128, "max": 57.42626953125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06702652114299347, "min": 0.06543292320560139, "max": 0.07623190031010714, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9383712960019086, "min": 0.5162683172675315, "max": 1.0344565482307957, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.005232142048626024, "min": 0.00014117326501944112, "max": 0.00907844625495403, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.07324998868076434, "min": 0.0018352524452527347, "max": 0.13617669382431047, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.79778311505714e-06, "min": 7.79778311505714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010916896361079998, "min": 0.00010916896361079998, "max": 0.0032596913134363, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10259922857142859, "min": 0.10259922857142859, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4363892000000003, "min": 1.3691136000000002, "max": 2.3865637000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002696629342857144, "min": 0.0002696629342857144, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003775281080000001, "min": 0.003775281080000001, "max": 0.10867771363, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01165024470537901, "min": 0.011171041056513786, "max": 0.27153438329696655, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16310343146324158, "min": 0.14522352814674377, "max": 1.9007407426834106, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 787.4, "min": 708.6304347826087, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31496.0, "min": 15984.0, "max": 32597.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.16230995673686266, "min": -1.0000000521540642, "max": 0.5954738693392795, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 6.492398269474506, "min": -32.000001668930054, "max": 27.391797989606857, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.16230995673686266, "min": -1.0000000521540642, "max": 0.5954738693392795, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 6.492398269474506, "min": -32.000001668930054, "max": 27.391797989606857, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0951108428533189, "min": 0.08726800752705649, "max": 5.326414233073592, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.804433714132756, "min": 3.3161842860281467, "max": 85.22262772917747, "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": "1709021890", "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 --force", "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": "1709024106" }, "total": 2215.646820139, "count": 1, "self": 0.47672017399963806, "children": { "run_training.setup": { "total": 0.050897230000373384, "count": 1, "self": 0.050897230000373384 }, "TrainerController.start_learning": { "total": 2215.119202735, "count": 1, "self": 1.8732796179247089, "children": { "TrainerController._reset_env": { "total": 2.1878470649999144, "count": 1, "self": 2.1878470649999144 }, "TrainerController.advance": { "total": 2210.9977124920742, "count": 63108, "self": 2.1442521380786275, "children": { "env_step": { "total": 1508.8486478859968, "count": 63108, "self": 1381.0182823819132, "children": { "SubprocessEnvManager._take_step": { "total": 126.61701843203355, "count": 63108, "self": 5.014552045979144, "children": { "TorchPolicy.evaluate": { "total": 121.6024663860544, "count": 62561, "self": 121.6024663860544 } } }, "workers": { "total": 1.2133470720500554, "count": 63108, "self": 0.0, "children": { "worker_root": { "total": 2211.083486517942, "count": 63108, "is_parallel": true, "self": 957.357672346785, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0014379790000020876, "count": 1, "is_parallel": true, "self": 0.00042715999916254077, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010108190008395468, "count": 8, "is_parallel": true, "self": 0.0010108190008395468 } } }, "UnityEnvironment.step": { "total": 0.051710159000322165, "count": 1, "is_parallel": true, "self": 0.0005890510001336224, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005217990001256112, "count": 1, "is_parallel": true, "self": 0.0005217990001256112 }, "communicator.exchange": { "total": 0.048970539000038116, "count": 1, "is_parallel": true, "self": 0.048970539000038116 }, "steps_from_proto": { "total": 0.001628770000024815, "count": 1, "is_parallel": true, "self": 0.00031503999889537226, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013137300011294428, "count": 8, "is_parallel": true, "self": 0.0013137300011294428 } } } } } } }, "UnityEnvironment.step": { "total": 1253.7258141711573, "count": 63107, "is_parallel": true, "self": 34.812066160063296, "children": { "UnityEnvironment._generate_step_input": { "total": 19.222566767983153, "count": 63107, "is_parallel": true, "self": 19.222566767983153 }, "communicator.exchange": { "total": 1103.482255593046, "count": 63107, "is_parallel": true, "self": 1103.482255593046 }, "steps_from_proto": { "total": 96.20892565006488, "count": 63107, "is_parallel": true, "self": 20.62595448093998, "children": { "_process_rank_one_or_two_observation": { "total": 75.5829711691249, "count": 504856, "is_parallel": true, "self": 75.5829711691249 } } } } } } } } } } }, "trainer_advance": { "total": 700.0048124679988, "count": 63108, "self": 3.437519116949261, "children": { "process_trajectory": { "total": 115.57986222505224, "count": 63108, "self": 115.43846021605259, "children": { "RLTrainer._checkpoint": { "total": 0.1414020089996484, "count": 2, "self": 0.1414020089996484 } } }, "_update_policy": { "total": 580.9874311259973, "count": 434, "self": 234.1384475130535, "children": { "TorchPPOOptimizer.update": { "total": 346.8489836129438, "count": 22824, "self": 346.8489836129438 } } } } } } }, "trainer_threads": { "total": 9.300001693191007e-07, "count": 1, "self": 9.300001693191007e-07 }, "TrainerController._save_models": { "total": 0.06036263000078179, "count": 1, "self": 0.0014258600012908573, "children": { "RLTrainer._checkpoint": { "total": 0.058936769999490934, "count": 1, "self": 0.058936769999490934 } } } } } } }