{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7248805165290833, "min": 0.6530888676643372, "max": 1.4960893392562866, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 21502.85546875, "min": 19561.318359375, "max": 45385.3671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.08370480686426163, "min": -0.10189813375473022, "max": 0.08370480686426163, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 21.093610763549805, "min": -24.557449340820312, "max": 21.093610763549805, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.024741623550653458, "min": 0.009940629824995995, "max": 0.2777886390686035, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.234889030456543, "min": 2.405632495880127, "max": 65.83590698242188, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0656030477839522, "min": 0.06493231750234273, "max": 0.07426485394351132, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9184426689753309, "min": 0.5198539776045792, "max": 1.0248139072620477, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.007910758734570186, "min": 6.077635974779715e-05, "max": 0.007910758734570186, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.11075062228398261, "min": 0.000790092676721363, "max": 0.11075062228398261, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.330340413728571e-06, "min": 7.330340413728571e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001026247657922, "min": 0.0001026247657922, "max": 0.0035070038309987996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244341428571431, "min": 0.10244341428571431, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342078000000003, "min": 1.3886848, "max": 2.5690011999999998, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002540970871428571, "min": 0.0002540970871428571, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00355735922, "min": 0.00355735922, "max": 0.11692321987999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01094376016408205, "min": 0.01022619940340519, "max": 0.2712734043598175, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15321263670921326, "min": 0.14316679537296295, "max": 1.898913860321045, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 746.6341463414634, "min": 746.6341463414634, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30612.0, "min": 15984.0, "max": 32874.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.3750731316281528, "min": -1.0000000521540642, "max": 0.3750731316281528, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 15.377998396754265, "min": -31.995201662182808, "max": 15.377998396754265, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.3750731316281528, "min": -1.0000000521540642, "max": 0.3750731316281528, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 15.377998396754265, "min": -31.995201662182808, "max": 15.377998396754265, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08554141918045012, "min": 0.08554141918045012, "max": 5.005493411328644, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.5071981863984547, "min": 3.1327646027493756, "max": 80.0878945812583, "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": "1696609645", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.21.2", "end_time_seconds": "1696611840" }, "total": 2194.424893917, "count": 1, "self": 0.492984587000592, "children": { "run_training.setup": { "total": 0.0440991440000289, "count": 1, "self": 0.0440991440000289 }, "TrainerController.start_learning": { "total": 2193.8878101859996, "count": 1, "self": 1.47574369200629, "children": { "TrainerController._reset_env": { "total": 3.579598270000133, "count": 1, "self": 3.579598270000133 }, "TrainerController.advance": { "total": 2188.7521914399936, "count": 63114, "self": 1.5681670929029679, "children": { "env_step": { "total": 1507.656660760948, "count": 63114, "self": 1375.6198978600437, "children": { "SubprocessEnvManager._take_step": { "total": 131.12824598791485, "count": 63114, "self": 4.802892964735747, "children": { "TorchPolicy.evaluate": { "total": 126.3253530231791, "count": 62556, "self": 126.3253530231791 } } }, "workers": { "total": 0.9085169129893984, "count": 63114, "self": 0.0, "children": { "worker_root": { "total": 2189.3344594818973, "count": 63114, "is_parallel": true, "self": 937.6351781969142, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001970524000171281, "count": 1, "is_parallel": true, "self": 0.0005895040007999341, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013810199993713468, "count": 8, "is_parallel": true, "self": 0.0013810199993713468 } } }, "UnityEnvironment.step": { "total": 0.0900659160001851, "count": 1, "is_parallel": true, "self": 0.0005683110002792091, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005227979995652277, "count": 1, "is_parallel": true, "self": 0.0005227979995652277 }, "communicator.exchange": { "total": 0.08691156700024294, "count": 1, "is_parallel": true, "self": 0.08691156700024294 }, "steps_from_proto": { "total": 0.0020632400000977213, "count": 1, "is_parallel": true, "self": 0.000550143000054959, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015130970000427624, "count": 8, "is_parallel": true, "self": 0.0015130970000427624 } } } } } } }, "UnityEnvironment.step": { "total": 1251.699281284983, "count": 63113, "is_parallel": true, "self": 35.01291587501146, "children": { "UnityEnvironment._generate_step_input": { "total": 25.23395277089685, "count": 63113, "is_parallel": true, "self": 25.23395277089685 }, "communicator.exchange": { "total": 1077.4386158251336, "count": 63113, "is_parallel": true, "self": 1077.4386158251336 }, "steps_from_proto": { "total": 114.0137968139411, "count": 63113, "is_parallel": true, "self": 22.75369214897455, "children": { "_process_rank_one_or_two_observation": { "total": 91.26010466496655, "count": 504904, "is_parallel": true, "self": 91.26010466496655 } } } } } } } } } } }, "trainer_advance": { "total": 679.5273635861427, "count": 63114, "self": 2.6699957400746825, "children": { "process_trajectory": { "total": 122.4624345430716, "count": 63114, "self": 122.27785316407153, "children": { "RLTrainer._checkpoint": { "total": 0.18458137900006477, "count": 2, "self": 0.18458137900006477 } } }, "_update_policy": { "total": 554.3949333029964, "count": 443, "self": 353.4021857530638, "children": { "TorchPPOOptimizer.update": { "total": 200.99274754993257, "count": 22812, "self": 200.99274754993257 } } } } } } }, "trainer_threads": { "total": 1.032999534800183e-06, "count": 1, "self": 1.032999534800183e-06 }, "TrainerController._save_models": { "total": 0.08027575100004469, "count": 1, "self": 0.0015157449997786898, "children": { "RLTrainer._checkpoint": { "total": 0.078760006000266, "count": 1, "self": 0.078760006000266 } } } } } } }