{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3784320652484894, "min": 0.3784320652484894, "max": 1.4468542337417603, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11419.56640625, "min": 11419.56640625, "max": 43891.76953125, "count": 33 }, "Pyramids.Step.mean": { "value": 989960.0, "min": 29952.0, "max": 989960.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989960.0, "min": 29952.0, "max": 989960.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5530080795288086, "min": -0.12447740137577057, "max": 0.577918291091919, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 154.84226989746094, "min": -30.123531341552734, "max": 160.66128540039062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.15004125237464905, "min": -0.15004125237464905, "max": 0.3633989989757538, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -42.01155090332031, "min": -42.01155090332031, "max": 86.12556457519531, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06416595795379165, "min": 0.06416595795379165, "max": 0.0766869312411907, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8983234113530831, "min": 0.5368085186883349, "max": 1.0916426900703478, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01907874156570281, "min": 0.0002271232122975655, "max": 0.019382130195305512, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.26710238191983937, "min": 0.003179724972165917, "max": 0.27134982273427716, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.71134028672857e-06, "min": 7.71134028672857e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010795876401419998, "min": 0.00010795876401419998, "max": 0.0036330409889864, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025704142857143, "min": 0.1025704142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359858, "min": 1.3886848, "max": 2.6110135999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002667843871428571, "min": 0.0002667843871428571, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037349814199999993, "min": 0.0037349814199999993, "max": 0.12112025864, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009951123036444187, "min": 0.009821628220379353, "max": 0.39340129494667053, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13931572437286377, "min": 0.1375027894973755, "max": 2.7538089752197266, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 336.12359550561797, "min": 331.4, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29915.0, "min": 15984.0, "max": 32780.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6189168322454677, "min": -1.0000000521540642, "max": 1.6637654172049627, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 144.08359806984663, "min": -31.99680168926716, "max": 152.5155982747674, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6189168322454677, "min": -1.0000000521540642, "max": 1.6637654172049627, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 144.08359806984663, "min": -31.99680168926716, "max": 152.5155982747674, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03461664142345439, "min": 0.034518609023775515, "max": 7.987418609671295, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.080881086687441, "min": 2.946949219709495, "max": 127.79869775474072, "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": "1717326992", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717329314" }, "total": 2321.492061666, "count": 1, "self": 1.2899267379998491, "children": { "run_training.setup": { "total": 0.07805429800009733, "count": 1, "self": 0.07805429800009733 }, "TrainerController.start_learning": { "total": 2320.12408063, "count": 1, "self": 1.5492367139759153, "children": { "TrainerController._reset_env": { "total": 2.5499198689999503, "count": 1, "self": 2.5499198689999503 }, "TrainerController.advance": { "total": 2315.897227130025, "count": 63795, "self": 1.515625379996436, "children": { "env_step": { "total": 1665.1059332879493, "count": 63795, "self": 1525.6340065519184, "children": { "SubprocessEnvManager._take_step": { "total": 138.5647952250181, "count": 63795, "self": 4.859348103999764, "children": { "TorchPolicy.evaluate": { "total": 133.70544712101832, "count": 62561, "self": 133.70544712101832 } } }, "workers": { "total": 0.9071315110127216, "count": 63795, "self": 0.0, "children": { "worker_root": { "total": 2314.521697573083, "count": 63795, "is_parallel": true, "self": 917.6147254540208, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020929290001276968, "count": 1, "is_parallel": true, "self": 0.0006722420002915896, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014206869998361071, "count": 8, "is_parallel": true, "self": 0.0014206869998361071 } } }, "UnityEnvironment.step": { "total": 0.04644736299997021, "count": 1, "is_parallel": true, "self": 0.0006249430000480061, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004590199998801836, "count": 1, "is_parallel": true, "self": 0.0004590199998801836 }, "communicator.exchange": { "total": 0.04375208900000871, "count": 1, "is_parallel": true, "self": 0.04375208900000871 }, "steps_from_proto": { "total": 0.0016113110000333108, "count": 1, "is_parallel": true, "self": 0.00033873099982884014, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012725800002044707, "count": 8, "is_parallel": true, "self": 0.0012725800002044707 } } } } } } }, "UnityEnvironment.step": { "total": 1396.9069721190624, "count": 63794, "is_parallel": true, "self": 35.82608438596435, "children": { "UnityEnvironment._generate_step_input": { "total": 23.6061170509538, "count": 63794, "is_parallel": true, "self": 23.6061170509538 }, "communicator.exchange": { "total": 1236.2046636470886, "count": 63794, "is_parallel": true, "self": 1236.2046636470886 }, "steps_from_proto": { "total": 101.27010703505562, "count": 63794, "is_parallel": true, "self": 20.922437292071663, "children": { "_process_rank_one_or_two_observation": { "total": 80.34766974298395, "count": 510352, "is_parallel": true, "self": 80.34766974298395 } } } } } } } } } } }, "trainer_advance": { "total": 649.2756684620792, "count": 63795, "self": 2.914044365076279, "children": { "process_trajectory": { "total": 131.0116828980008, "count": 63795, "self": 130.7706679100006, "children": { "RLTrainer._checkpoint": { "total": 0.24101498800018817, "count": 2, "self": 0.24101498800018817 } } }, "_update_policy": { "total": 515.3499411990022, "count": 453, "self": 303.00448341001015, "children": { "TorchPPOOptimizer.update": { "total": 212.345457788992, "count": 22842, "self": 212.345457788992 } } } } } } }, "trainer_threads": { "total": 1.2809996405849233e-06, "count": 1, "self": 1.2809996405849233e-06 }, "TrainerController._save_models": { "total": 0.12769563599977118, "count": 1, "self": 0.0018743040000117617, "children": { "RLTrainer._checkpoint": { "total": 0.12582133199975942, "count": 1, "self": 0.12582133199975942 } } } } } } }