{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7488517761230469, "min": 0.6447844505310059, "max": 1.5459904670715332, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 22393.6640625, "min": 19271.318359375, "max": 46899.16796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989872.0, "min": 29952.0, "max": 989872.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989872.0, "min": 29952.0, "max": 989872.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.019289691001176834, "min": -0.10402826964855194, "max": 0.04871964454650879, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 4.725974082946777, "min": -24.966785430908203, "max": 11.887593269348145, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008578427135944366, "min": -0.007467157207429409, "max": 0.15129059553146362, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.101714611053467, "min": -1.7697162628173828, "max": 36.30974197387695, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06973546571499975, "min": 0.06537674973998121, "max": 0.07336444405777964, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9762965200099966, "min": 0.49905418185082306, "max": 1.0727976258203853, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.004404868398465874, "min": 2.3950339148027197e-05, "max": 0.004720671249880307, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.06166815757852224, "min": 0.0003592550872204079, "max": 0.06608939749832429, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.324533272807142e-06, "min": 7.324533272807142e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010254346581929999, "min": 0.00010254346581929999, "max": 0.0032603807132064993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244147857142857, "min": 0.10244147857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341807, "min": 1.3691136000000002, "max": 2.3867935000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002539037092857143, "min": 0.0002539037092857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035546519300000004, "min": 0.0035546519300000004, "max": 0.10870067065, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011813228018581867, "min": 0.011813228018581867, "max": 0.2889266312122345, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1653851866722107, "min": 0.1653851866722107, "max": 2.022486448287964, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 852.3421052631579, "min": 842.6578947368421, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32389.0, "min": 15984.0, "max": 32389.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.22116319972433543, "min": -1.0000000521540642, "max": -0.158852681517601, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -8.404201589524746, "min": -32.000001668930054, "max": -6.0364018976688385, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.22116319972433543, "min": -1.0000000521540642, "max": -0.158852681517601, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -8.404201589524746, "min": -32.000001668930054, "max": -6.0364018976688385, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.10468380591881118, "min": 0.10468380591881118, "max": 5.415352387353778, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.977984624914825, "min": 3.644634314114228, "max": 86.64563819766045, "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": "1756043291", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1756047050" }, "total": 3758.784336188, "count": 1, "self": 1.4299364990001777, "children": { "run_training.setup": { "total": 0.05578594000007797, "count": 1, "self": 0.05578594000007797 }, "TrainerController.start_learning": { "total": 3757.2986137489997, "count": 1, "self": 2.972953364021123, "children": { "TrainerController._reset_env": { "total": 3.8633677860002535, "count": 1, "self": 3.8633677860002535 }, "TrainerController.advance": { "total": 3750.319426425978, "count": 63160, "self": 3.167747282931032, "children": { "env_step": { "total": 2438.8047455879855, "count": 63160, "self": 2228.4151067950697, "children": { "SubprocessEnvManager._take_step": { "total": 208.6100466389289, "count": 63160, "self": 10.403559045033944, "children": { "TorchPolicy.evaluate": { "total": 198.20648759389496, "count": 62568, "self": 198.20648759389496 } } }, "workers": { "total": 1.7795921539868687, "count": 63160, "self": 0.0, "children": { "worker_root": { "total": 3746.5845889058796, "count": 63160, "is_parallel": true, "self": 1738.4553816398065, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0037214529997982027, "count": 1, "is_parallel": true, "self": 0.0013413769997896452, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023800760000085575, "count": 8, "is_parallel": true, "self": 0.0023800760000085575 } } }, "UnityEnvironment.step": { "total": 0.07902737299991713, "count": 1, "is_parallel": true, "self": 0.0007203630002550199, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005590229998233553, "count": 1, "is_parallel": true, "self": 0.0005590229998233553 }, "communicator.exchange": { "total": 0.07567841799982489, "count": 1, "is_parallel": true, "self": 0.07567841799982489 }, "steps_from_proto": { "total": 0.002069569000013871, "count": 1, "is_parallel": true, "self": 0.0004698779998761893, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015996910001376818, "count": 8, "is_parallel": true, "self": 0.0015996910001376818 } } } } } } }, "UnityEnvironment.step": { "total": 2008.129207266073, "count": 63159, "is_parallel": true, "self": 53.55146999118733, "children": { "UnityEnvironment._generate_step_input": { "total": 34.69607676503256, "count": 63159, "is_parallel": true, "self": 34.69607676503256 }, "communicator.exchange": { "total": 1772.9666636139295, "count": 63159, "is_parallel": true, "self": 1772.9666636139295 }, "steps_from_proto": { "total": 146.91499689592365, "count": 63159, "is_parallel": true, "self": 32.5446596998504, "children": { "_process_rank_one_or_two_observation": { "total": 114.37033719607325, "count": 505272, "is_parallel": true, "self": 114.37033719607325 } } } } } } } } } } }, "trainer_advance": { "total": 1308.3469335550612, "count": 63160, "self": 5.622210516978612, "children": { "process_trajectory": { "total": 200.20308955808787, "count": 63160, "self": 199.86270891208778, "children": { "RLTrainer._checkpoint": { "total": 0.3403806460000851, "count": 2, "self": 0.3403806460000851 } } }, "_update_policy": { "total": 1102.5216334799948, "count": 439, "self": 421.2265963449954, "children": { "TorchPPOOptimizer.update": { "total": 681.2950371349993, "count": 22827, "self": 681.2950371349993 } } } } } } }, "trainer_threads": { "total": 1.5539999367319979e-06, "count": 1, "self": 1.5539999367319979e-06 }, "TrainerController._save_models": { "total": 0.1428646190006475, "count": 1, "self": 0.0066819500007113675, "children": { "RLTrainer._checkpoint": { "total": 0.13618266899993614, "count": 1, "self": 0.13618266899993614 } } } } } } }