{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6126883029937744, "min": 0.6126883029937744, "max": 1.4967542886734009, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18312.02734375, "min": 18312.02734375, "max": 45405.5390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989918.0, "min": 29952.0, "max": 989918.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989918.0, "min": 29952.0, "max": 989918.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5324720144271851, "min": -0.11560316383838654, "max": 0.5324720144271851, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 148.5596923828125, "min": -27.754396438598633, "max": 148.5596923828125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.023038864135742188, "min": -0.030367037281394005, "max": 0.1841537356376648, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -6.42784309387207, "min": -8.077631950378418, "max": 44.196895599365234, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06815869971064341, "min": 0.06424883157818666, "max": 0.07461446524312437, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0223804956596512, "min": 0.46968057515128414, "max": 1.0501115527392053, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01604219980578218, "min": 0.00012896050009038491, "max": 0.016694838845675505, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24063299708673272, "min": 0.001418565500994234, "max": 0.25042258268513257, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.500757499780004e-06, "min": 7.500757499780004e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011251136249670006, "min": 0.00011251136249670006, "max": 0.0029082534305823, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250022, "min": 0.10250022, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375033, "min": 1.327104, "max": 2.3588581, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002597719780000001, "min": 0.0002597719780000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003896579670000002, "min": 0.003896579670000002, "max": 0.09697482823, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00828477367758751, "min": 0.007894960232079029, "max": 0.32767465710639954, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12427160888910294, "min": 0.11142752319574356, "max": 2.293722629547119, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 377.24050632911394, "min": 341.9529411764706, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29802.0, "min": 15984.0, "max": 33732.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5974354306353797, "min": -1.0000000521540642, "max": 1.6101761756553536, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 126.19739902019501, "min": -32.000001668930054, "max": 135.2547987550497, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5974354306353797, "min": -1.0000000521540642, "max": 1.6101761756553536, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 126.19739902019501, "min": -32.000001668930054, "max": 135.2547987550497, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.032722644502358934, "min": 0.029330553021974907, "max": 6.355139321647584, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.585088915686356, "min": 2.4473799957777373, "max": 101.68222914636135, "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": "1750692564", "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": "1750694688" }, "total": 2124.4359373409998, "count": 1, "self": 0.6295183059996816, "children": { "run_training.setup": { "total": 0.019953628000166646, "count": 1, "self": 0.019953628000166646 }, "TrainerController.start_learning": { "total": 2123.786465407, "count": 1, "self": 1.2684719549897636, "children": { "TrainerController._reset_env": { "total": 2.2071717569997418, "count": 1, "self": 2.2071717569997418 }, "TrainerController.advance": { "total": 2120.2243714860097, "count": 63601, "self": 1.3734275539741247, "children": { "env_step": { "total": 1458.3620975779754, "count": 63601, "self": 1308.7893987060347, "children": { "SubprocessEnvManager._take_step": { "total": 148.76214043303662, "count": 63601, "self": 4.539075225120541, "children": { "TorchPolicy.evaluate": { "total": 144.22306520791608, "count": 62571, "self": 144.22306520791608 } } }, "workers": { "total": 0.8105584389040814, "count": 63601, "self": 0.0, "children": { "worker_root": { "total": 2117.6063016780354, "count": 63601, "is_parallel": true, "self": 921.3897593689426, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002005840000038006, "count": 1, "is_parallel": true, "self": 0.0006528660001094977, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013529739999285084, "count": 8, "is_parallel": true, "self": 0.0013529739999285084 } } }, "UnityEnvironment.step": { "total": 0.05170061899980283, "count": 1, "is_parallel": true, "self": 0.0005778269992333662, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004988230002709315, "count": 1, "is_parallel": true, "self": 0.0004988230002709315 }, "communicator.exchange": { "total": 0.04890622600032657, "count": 1, "is_parallel": true, "self": 0.04890622600032657 }, "steps_from_proto": { "total": 0.0017177429999719607, "count": 1, "is_parallel": true, "self": 0.00035607600102594006, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013616669989460206, "count": 8, "is_parallel": true, "self": 0.0013616669989460206 } } } } } } }, "UnityEnvironment.step": { "total": 1196.2165423090928, "count": 63600, "is_parallel": true, "self": 31.443030987065868, "children": { "UnityEnvironment._generate_step_input": { "total": 23.023301468958834, "count": 63600, "is_parallel": true, "self": 23.023301468958834 }, "communicator.exchange": { "total": 1045.7261954270557, "count": 63600, "is_parallel": true, "self": 1045.7261954270557 }, "steps_from_proto": { "total": 96.0240144260124, "count": 63600, "is_parallel": true, "self": 19.067313577972072, "children": { "_process_rank_one_or_two_observation": { "total": 76.95670084804033, "count": 508800, "is_parallel": true, "self": 76.95670084804033 } } } } } } } } } } }, "trainer_advance": { "total": 660.4888463540601, "count": 63601, "self": 2.3370834090733297, "children": { "process_trajectory": { "total": 124.64857908698787, "count": 63601, "self": 124.44491116198742, "children": { "RLTrainer._checkpoint": { "total": 0.2036679250004454, "count": 2, "self": 0.2036679250004454 } } }, "_update_policy": { "total": 533.5031838579989, "count": 427, "self": 298.39569530894005, "children": { "TorchPPOOptimizer.update": { "total": 235.10748854905887, "count": 22851, "self": 235.10748854905887 } } } } } } }, "trainer_threads": { "total": 9.929999578162096e-07, "count": 1, "self": 9.929999578162096e-07 }, "TrainerController._save_models": { "total": 0.08644921600080124, "count": 1, "self": 0.0013331140007721842, "children": { "RLTrainer._checkpoint": { "total": 0.08511610200002906, "count": 1, "self": 0.08511610200002906 } } } } } } }