{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5318188071250916, "min": 0.5318188071250916, "max": 1.462334156036377, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16090.708984375, "min": 16090.708984375, "max": 44361.3671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989994.0, "min": 29952.0, "max": 989994.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989994.0, "min": 29952.0, "max": 989994.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5258587598800659, "min": -0.12296944111585617, "max": 0.5625362396240234, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 145.13702392578125, "min": -29.635635375976562, "max": 155.8856658935547, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01571180298924446, "min": -0.016020892187952995, "max": 0.556074321269989, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.3364577293396, "min": -4.453807830810547, "max": 131.78961181640625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0657582720963373, "min": 0.0657582720963373, "max": 0.07558391838371202, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9206158093487222, "min": 0.5018633903775648, "max": 1.0554582269202608, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015438570941374305, "min": 0.00012763055785764644, "max": 0.015438570941374305, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21613999317924026, "min": 0.0015315666942917572, "max": 0.21613999317924026, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.343797552099998e-06, "min": 7.343797552099998e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010281316572939996, "min": 0.00010281316572939996, "max": 0.0035073341308886996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244790000000001, "min": 0.10244790000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342706, "min": 1.3691136000000002, "max": 2.5691113000000008, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002545452099999999, "min": 0.0002545452099999999, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035636329399999986, "min": 0.0035636329399999986, "max": 0.11693421887000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007864792831242085, "min": 0.00762632442638278, "max": 0.5289080142974854, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11010710150003433, "min": 0.10676854103803635, "max": 3.7023561000823975, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 350.34090909090907, "min": 349.9294117647059, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30830.0, "min": 15984.0, "max": 32902.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5814590758898042, "min": -1.0000000521540642, "max": 1.6035475995214212, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 139.16839867830276, "min": -32.000001668930054, "max": 139.16839867830276, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5814590758898042, "min": -1.0000000521540642, "max": 1.6035475995214212, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 139.16839867830276, "min": -32.000001668930054, "max": 139.16839867830276, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.029267472062863155, "min": 0.029267472062863155, "max": 11.732497911900282, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.5755375415319577, "min": 2.192244323930936, "max": 187.7199665904045, "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": "1704284203", "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=PyramidsRND1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704286740" }, "total": 2536.520758479, "count": 1, "self": 0.6439807589999873, "children": { "run_training.setup": { "total": 0.0629830190000007, "count": 1, "self": 0.0629830190000007 }, "TrainerController.start_learning": { "total": 2535.813794701, "count": 1, "self": 1.8015315219645345, "children": { "TrainerController._reset_env": { "total": 2.143176939, "count": 1, "self": 2.143176939 }, "TrainerController.advance": { "total": 2531.7670921180356, "count": 63742, "self": 1.87392134998845, "children": { "env_step": { "total": 1841.7583996840606, "count": 63742, "self": 1684.8403092420197, "children": { "SubprocessEnvManager._take_step": { "total": 155.81387656804304, "count": 63742, "self": 5.631579634046375, "children": { "TorchPolicy.evaluate": { "total": 150.18229693399667, "count": 62558, "self": 150.18229693399667 } } }, "workers": { "total": 1.1042138739978782, "count": 63742, "self": 0.0, "children": { "worker_root": { "total": 2529.4408955630083, "count": 63742, "is_parallel": true, "self": 990.2356652370395, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001889930999993794, "count": 1, "is_parallel": true, "self": 0.0006548750001229564, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012350559998708377, "count": 8, "is_parallel": true, "self": 0.0012350559998708377 } } }, "UnityEnvironment.step": { "total": 0.053517554999984895, "count": 1, "is_parallel": true, "self": 0.0006302009999785696, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004979670000011538, "count": 1, "is_parallel": true, "self": 0.0004979670000011538 }, "communicator.exchange": { "total": 0.05024646900000107, "count": 1, "is_parallel": true, "self": 0.05024646900000107 }, "steps_from_proto": { "total": 0.0021429180000041015, "count": 1, "is_parallel": true, "self": 0.0004069160000312877, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017360019999728138, "count": 8, "is_parallel": true, "self": 0.0017360019999728138 } } } } } } }, "UnityEnvironment.step": { "total": 1539.2052303259688, "count": 63741, "is_parallel": true, "self": 40.01114626904587, "children": { "UnityEnvironment._generate_step_input": { "total": 28.31541143498356, "count": 63741, "is_parallel": true, "self": 28.31541143498356 }, "communicator.exchange": { "total": 1352.5783149799386, "count": 63741, "is_parallel": true, "self": 1352.5783149799386 }, "steps_from_proto": { "total": 118.30035764200073, "count": 63741, "is_parallel": true, "self": 25.088557057951334, "children": { "_process_rank_one_or_two_observation": { "total": 93.2118005840494, "count": 509928, "is_parallel": true, "self": 93.2118005840494 } } } } } } } } } } }, "trainer_advance": { "total": 688.1347710839865, "count": 63742, "self": 3.4618504369074117, "children": { "process_trajectory": { "total": 142.42609257808095, "count": 63742, "self": 142.1971216580808, "children": { "RLTrainer._checkpoint": { "total": 0.22897092000016528, "count": 2, "self": 0.22897092000016528 } } }, "_update_policy": { "total": 542.2468280689981, "count": 448, "self": 324.2574124640102, "children": { "TorchPPOOptimizer.update": { "total": 217.98941560498787, "count": 22857, "self": 217.98941560498787 } } } } } } }, "trainer_threads": { "total": 1.1349998203513678e-06, "count": 1, "self": 1.1349998203513678e-06 }, "TrainerController._save_models": { "total": 0.10199298699990322, "count": 1, "self": 0.0017225269998561998, "children": { "RLTrainer._checkpoint": { "total": 0.10027046000004702, "count": 1, "self": 0.10027046000004702 } } } } } } }