{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.435935914516449, "min": 0.4213733673095703, "max": 1.390051007270813, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13161.77734375, "min": 12715.3623046875, "max": 42168.5859375, "count": 33 }, "Pyramids.Step.mean": { "value": 989984.0, "min": 29952.0, "max": 989984.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989984.0, "min": 29952.0, "max": 989984.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3185103237628937, "min": -0.0947466641664505, "max": 0.45888981223106384, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 83.44970703125, "min": -22.928691864013672, "max": 122.98246765136719, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.030679401010274887, "min": -0.03833285719156265, "max": 0.3219869136810303, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.038002967834473, "min": -10.388204574584961, "max": 77.59884643554688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06979774181163316, "min": 0.06623267750200328, "max": 0.07352059617569197, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9771683853628643, "min": 0.5146441732298438, "max": 1.0854656835629914, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011916276192949566, "min": 0.0009966640639475918, "max": 0.013191068361715328, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16682786670129393, "min": 0.012956632831318694, "max": 0.19786602542572992, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.282340429728572e-06, "min": 7.282340429728572e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001019527660162, "min": 0.0001019527660162, "max": 0.0035071196309602, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242741428571431, "min": 0.10242741428571431, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339838000000003, "min": 1.3886848, "max": 2.5690398, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002524986871428572, "min": 0.0002524986871428572, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035349816200000005, "min": 0.0035349816200000005, "max": 0.11692707601999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007213735021650791, "min": 0.007059289142489433, "max": 0.3894733786582947, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10099229216575623, "min": 0.10099229216575623, "max": 2.726313591003418, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 468.84615384615387, "min": 434.5217391304348, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30475.0, "min": 15984.0, "max": 32902.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.0684605789455501, "min": -1.0000000521540642, "max": 1.4157617486575071, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 70.5183982104063, "min": -29.997601568698883, "max": 98.51399824023247, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.0684605789455501, "min": -1.0000000521540642, "max": 1.4157617486575071, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 70.5183982104063, "min": -29.997601568698883, "max": 98.51399824023247, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03525093159546624, "min": 0.034974775920896456, "max": 7.668156085535884, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.326561485300772, "min": 2.1767208746168762, "max": 122.69049736857414, "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": "1724515309", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1724517564" }, "total": 2255.441398202, "count": 1, "self": 0.476132029999917, "children": { "run_training.setup": { "total": 0.05323798499989607, "count": 1, "self": 0.05323798499989607 }, "TrainerController.start_learning": { "total": 2254.912028187, "count": 1, "self": 1.5806336990176533, "children": { "TrainerController._reset_env": { "total": 2.0885575190000054, "count": 1, "self": 2.0885575190000054 }, "TrainerController.advance": { "total": 2251.1569353709824, "count": 63674, "self": 1.680537942934734, "children": { "env_step": { "total": 1593.7604527870237, "count": 63674, "self": 1448.775508080011, "children": { "SubprocessEnvManager._take_step": { "total": 144.01518980801347, "count": 63674, "self": 5.024245855046956, "children": { "TorchPolicy.evaluate": { "total": 138.99094395296652, "count": 62547, "self": 138.99094395296652 } } }, "workers": { "total": 0.9697548989993265, "count": 63674, "self": 0.0, "children": { "worker_root": { "total": 2249.452297531949, "count": 63674, "is_parallel": true, "self": 931.0677311609898, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002127320999989024, "count": 1, "is_parallel": true, "self": 0.0007352200000241282, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013921009999648959, "count": 8, "is_parallel": true, "self": 0.0013921009999648959 } } }, "UnityEnvironment.step": { "total": 0.07180084900005568, "count": 1, "is_parallel": true, "self": 0.0006310430001121858, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046396199991249887, "count": 1, "is_parallel": true, "self": 0.00046396199991249887 }, "communicator.exchange": { "total": 0.0688994699999057, "count": 1, "is_parallel": true, "self": 0.0688994699999057 }, "steps_from_proto": { "total": 0.0018063740001252881, "count": 1, "is_parallel": true, "self": 0.000375905000282728, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014304689998425602, "count": 8, "is_parallel": true, "self": 0.0014304689998425602 } } } } } } }, "UnityEnvironment.step": { "total": 1318.3845663709594, "count": 63673, "is_parallel": true, "self": 35.01980330987681, "children": { "UnityEnvironment._generate_step_input": { "total": 24.757310351068554, "count": 63673, "is_parallel": true, "self": 24.757310351068554 }, "communicator.exchange": { "total": 1154.0818827359622, "count": 63673, "is_parallel": true, "self": 1154.0818827359622 }, "steps_from_proto": { "total": 104.5255699740519, "count": 63673, "is_parallel": true, "self": 21.971425594896118, "children": { "_process_rank_one_or_two_observation": { "total": 82.55414437915579, "count": 509384, "is_parallel": true, "self": 82.55414437915579 } } } } } } } } } } }, "trainer_advance": { "total": 655.7159446410242, "count": 63674, "self": 2.9970947040508236, "children": { "process_trajectory": { "total": 135.11948154497077, "count": 63674, "self": 134.90320173397095, "children": { "RLTrainer._checkpoint": { "total": 0.21627981099982208, "count": 2, "self": 0.21627981099982208 } } }, "_update_policy": { "total": 517.5993683920026, "count": 452, "self": 306.53042027901597, "children": { "TorchPPOOptimizer.update": { "total": 211.06894811298662, "count": 22734, "self": 211.06894811298662 } } } } } } }, "trainer_threads": { "total": 8.570000318286475e-07, "count": 1, "self": 8.570000318286475e-07 }, "TrainerController._save_models": { "total": 0.08590074099993217, "count": 1, "self": 0.0012907669997730409, "children": { "RLTrainer._checkpoint": { "total": 0.08460997400015913, "count": 1, "self": 0.08460997400015913 } } } } } } }