{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5869534611701965, "min": 0.5869534611701965, "max": 1.382928490638733, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17749.47265625, "min": 17731.7890625, "max": 41952.51953125, "count": 33 }, "Pyramids.Step.mean": { "value": 989982.0, "min": 29952.0, "max": 989982.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989982.0, "min": 29952.0, "max": 989982.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.26657140254974365, "min": -0.09772180765867233, "max": 0.2731958031654358, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 69.57513427734375, "min": -23.45323371887207, "max": 69.66493225097656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.10352865606546402, "min": -0.056626126170158386, "max": 0.3655428886413574, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 27.020978927612305, "min": -14.439661979675293, "max": 86.6336669921875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0682973407393733, "min": 0.06438571505880877, "max": 0.07480637028548247, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9561627703512261, "min": 0.46316986805097005, "max": 1.0533935562228125, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0211634631214569, "min": 4.81687363239384e-05, "max": 0.0211634631214569, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2962884837003966, "min": 0.0006261935722111993, "max": 0.2962884837003966, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.429576094935716e-06, "min": 7.429576094935716e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010401406532910002, "min": 0.00010401406532910002, "max": 0.0033827846724052003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247649285714287, "min": 0.10247649285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346709000000002, "min": 1.3691136000000002, "max": 2.5275948000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002574016364285715, "min": 0.0002574016364285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003603622910000001, "min": 0.003603622910000001, "max": 0.11278672052, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009306291118264198, "min": 0.009241444058716297, "max": 0.4796140491962433, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13028807938098907, "min": 0.1293802112340927, "max": 3.3572983741760254, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 522.3333333333334, "min": 522.3333333333334, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29773.0, "min": 15984.0, "max": 34308.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1617648953147102, "min": -1.0000000521540642, "max": 1.1617648953147102, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 66.22059903293848, "min": -32.000001668930054, "max": 66.22059903293848, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1617648953147102, "min": -1.0000000521540642, "max": 1.1617648953147102, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 66.22059903293848, "min": -32.000001668930054, "max": 66.22059903293848, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05056268563534934, "min": 0.05056268563534934, "max": 9.58631225116551, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8820730812149122, "min": 2.8820730812149122, "max": 153.38099601864815, "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": "1751280620", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1751282816" }, "total": 2195.576563118, "count": 1, "self": 0.5288320109998494, "children": { "run_training.setup": { "total": 0.01944851899997957, "count": 1, "self": 0.01944851899997957 }, "TrainerController.start_learning": { "total": 2195.0282825880004, "count": 1, "self": 1.5870483649919152, "children": { "TrainerController._reset_env": { "total": 2.175566789000186, "count": 1, "self": 2.175566789000186 }, "TrainerController.advance": { "total": 2191.1760364130087, "count": 63348, "self": 1.7054617419335045, "children": { "env_step": { "total": 1528.4774495610184, "count": 63348, "self": 1359.3763584049861, "children": { "SubprocessEnvManager._take_step": { "total": 168.09879207100607, "count": 63348, "self": 4.979234578034038, "children": { "TorchPolicy.evaluate": { "total": 163.11955749297204, "count": 62558, "self": 163.11955749297204 } } }, "workers": { "total": 1.0022990850261522, "count": 63348, "self": 0.0, "children": { "worker_root": { "total": 2189.1492704051, "count": 63348, "is_parallel": true, "self": 954.4946783750713, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017755220001163252, "count": 1, "is_parallel": true, "self": 0.0005649670004004292, "children": { "_process_rank_one_or_two_observation": { "total": 0.001210554999715896, "count": 8, "is_parallel": true, "self": 0.001210554999715896 } } }, "UnityEnvironment.step": { "total": 0.048064225999951304, "count": 1, "is_parallel": true, "self": 0.0005286070002057386, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004211209998175036, "count": 1, "is_parallel": true, "self": 0.0004211209998175036 }, "communicator.exchange": { "total": 0.04531214300004649, "count": 1, "is_parallel": true, "self": 0.04531214300004649 }, "steps_from_proto": { "total": 0.0018023549998815724, "count": 1, "is_parallel": true, "self": 0.0003628080000908085, "children": { "_process_rank_one_or_two_observation": { "total": 0.001439546999790764, "count": 8, "is_parallel": true, "self": 0.001439546999790764 } } } } } } }, "UnityEnvironment.step": { "total": 1234.6545920300289, "count": 63347, "is_parallel": true, "self": 33.66258004015049, "children": { "UnityEnvironment._generate_step_input": { "total": 24.020878633020857, "count": 63347, "is_parallel": true, "self": 24.020878633020857 }, "communicator.exchange": { "total": 1074.6173034189362, "count": 63347, "is_parallel": true, "self": 1074.6173034189362 }, "steps_from_proto": { "total": 102.35382993792132, "count": 63347, "is_parallel": true, "self": 21.369895891964234, "children": { "_process_rank_one_or_two_observation": { "total": 80.98393404595708, "count": 506776, "is_parallel": true, "self": 80.98393404595708 } } } } } } } } } } }, "trainer_advance": { "total": 660.993125110057, "count": 63348, "self": 2.9881354040155657, "children": { "process_trajectory": { "total": 127.02141311804576, "count": 63348, "self": 126.76964696304572, "children": { "RLTrainer._checkpoint": { "total": 0.2517661550000412, "count": 2, "self": 0.2517661550000412 } } }, "_update_policy": { "total": 530.9835765879957, "count": 441, "self": 295.03956352500404, "children": { "TorchPPOOptimizer.update": { "total": 235.94401306299164, "count": 22791, "self": 235.94401306299164 } } } } } } }, "trainer_threads": { "total": 1.0459998520673253e-06, "count": 1, "self": 1.0459998520673253e-06 }, "TrainerController._save_models": { "total": 0.08962997499975245, "count": 1, "self": 0.0013787949997094984, "children": { "RLTrainer._checkpoint": { "total": 0.08825118000004295, "count": 1, "self": 0.08825118000004295 } } } } } } }