{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7895178198814392, "min": 0.7515867948532104, "max": 1.5797045230865479, "count": 10 }, "Pyramids.Policy.Entropy.sum": { "value": 8438.3662109375, "min": 7279.5654296875, "max": 16176.1748046875, "count": 10 }, "Pyramids.Step.mean": { "value": 99954.0, "min": 9984.0, "max": 99954.0, "count": 10 }, "Pyramids.Step.sum": { "value": 99954.0, "min": 9984.0, "max": 99954.0, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.09259536862373352, "min": -0.09259536862373352, "max": 0.10429101437330246, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -7.500224590301514, "min": -7.500224590301514, "max": 8.134698867797852, "count": 10 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.3457752764225006, "min": 0.2897959351539612, "max": 0.9334814548492432, "count": 10 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 28.007797241210938, "min": 22.604082107543945, "max": 72.81155395507812, "count": 10 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07654318980723769, "min": 0.06493563851206603, "max": 0.07656713032659301, "count": 10 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.30617275922895076, "min": 0.13388598165287496, "max": 0.30626852130637205, "count": 10 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0007154271561261293, "min": 0.000595342603354911, "max": 0.06870893137723517, "count": 10 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0028617086245045172, "min": 0.002381370413419644, "max": 0.13741786275447035, "count": 10 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5546094817999992e-05, "min": 1.5546094817999992e-05, "max": 0.00028156800614399997, "count": 10 }, "Pyramids.Policy.LearningRate.sum": { "value": 6.218437927199997e-05, "min": 6.218437927199997e-05, "max": 0.0006822720725759999, "count": 10 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.105182, "min": 0.105182, "max": 0.19385600000000003, "count": 10 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.420728, "min": 0.3319039999999999, "max": 0.625169, "count": 10 }, "Pyramids.Policy.Beta.mean": { "value": 0.0005276817999999997, "min": 0.0005276817999999997, "max": 0.0093862144, "count": 10 }, "Pyramids.Policy.Beta.sum": { "value": 0.002110727199999999, "min": 0.002110727199999999, "max": 0.0227496576, "count": 10 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.13519787788391113, "min": 0.13519787788391113, "max": 0.9297571182250977, "count": 10 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.5407915115356445, "min": 0.5407915115356445, "max": 1.8595142364501953, "count": 10 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 780.6666666666666, "max": 999.0, "count": 8 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 12987.0, "min": 1578.0, "max": 15984.0, "count": 8 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -1.0000000521540642, "min": -1.0000000521540642, "max": 0.5523999681075414, "count": 8 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -13.000000678002834, "min": -16.000000834465027, "max": 1.6571999043226242, "count": 8 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -1.0000000521540642, "min": -1.0000000521540642, "max": 0.5523999681075414, "count": 8 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -13.000000678002834, "min": -16.000000834465027, "max": 1.6571999043226242, "count": 8 }, "Pyramids.Policy.RndReward.mean": { "value": 2.866085695532652, "min": 2.5438888669013977, "max": 21.107619432732463, "count": 8 }, "Pyramids.Policy.RndReward.sum": { "value": 37.25911404192448, "min": 7.631666600704193, "max": 337.7219109237194, "count": 8 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1766473729", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /kaggle/input/config/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "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": "1766473901" }, "total": 171.939794528, "count": 1, "self": 0.38431996999997864, "children": { "run_training.setup": { "total": 0.02551298499997756, "count": 1, "self": 0.02551298499997756 }, "TrainerController.start_learning": { "total": 171.52996157300004, "count": 1, "self": 0.13027753800224673, "children": { "TrainerController._reset_env": { "total": 2.296813643000064, "count": 1, "self": 2.296813643000064 }, "TrainerController.advance": { "total": 169.0221609369977, "count": 6316, "self": 0.14351905198498116, "children": { "env_step": { "total": 107.95740983600206, "count": 6316, "self": 93.03815747000738, "children": { "SubprocessEnvManager._take_step": { "total": 14.840473939993558, "count": 6316, "self": 0.4509838379907478, "children": { "TorchPolicy.evaluate": { "total": 14.38949010200281, "count": 6308, "self": 14.38949010200281 } } }, "workers": { "total": 0.07877842600112217, "count": 6316, "self": 0.0, "children": { "worker_root": { "total": 171.14462107799943, "count": 6316, "is_parallel": true, "self": 87.82382939499905, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0053696259999469476, "count": 1, "is_parallel": true, "self": 0.0038656059999766512, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015040199999702963, "count": 8, "is_parallel": true, "self": 0.0015040199999702963 } } }, "UnityEnvironment.step": { "total": 0.05440178499998183, "count": 1, "is_parallel": true, "self": 0.0005605229999900985, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005819299999529903, "count": 1, "is_parallel": true, "self": 0.0005819299999529903 }, "communicator.exchange": { "total": 0.051479964000009204, "count": 1, "is_parallel": true, "self": 0.051479964000009204 }, "steps_from_proto": { "total": 0.0017793680000295353, "count": 1, "is_parallel": true, "self": 0.0003873000000567117, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013920679999728236, "count": 8, "is_parallel": true, "self": 0.0013920679999728236 } } } } } } }, "UnityEnvironment.step": { "total": 83.32079168300038, "count": 6315, "is_parallel": true, "self": 2.180536337996955, "children": { "UnityEnvironment._generate_step_input": { "total": 1.4924747110030694, "count": 6315, "is_parallel": true, "self": 1.4924747110030694 }, "communicator.exchange": { "total": 73.25828614800139, "count": 6315, "is_parallel": true, "self": 73.25828614800139 }, "steps_from_proto": { "total": 6.389494485998966, "count": 6315, "is_parallel": true, "self": 1.3404905780022318, "children": { "_process_rank_one_or_two_observation": { "total": 5.049003907996735, "count": 50520, "is_parallel": true, "self": 5.049003907996735 } } } } } } } } } } }, "trainer_advance": { "total": 60.921232049010655, "count": 6316, "self": 0.16756583200640307, "children": { "process_trajectory": { "total": 11.564451606004354, "count": 6316, "self": 11.373344707004435, "children": { "RLTrainer._checkpoint": { "total": 0.1911068989999194, "count": 2, "self": 0.1911068989999194 } } }, "_update_policy": { "total": 49.1892146109999, "count": 33, "self": 26.784854103002203, "children": { "TorchPPOOptimizer.update": { "total": 22.404360507997694, "count": 2283, "self": 22.404360507997694 } } } } } } }, "trainer_threads": { "total": 1.0610000344968284e-06, "count": 1, "self": 1.0610000344968284e-06 }, "TrainerController._save_models": { "total": 0.0807083939999984, "count": 1, "self": 0.0015529369999285336, "children": { "RLTrainer._checkpoint": { "total": 0.07915545700006987, "count": 1, "self": 0.07915545700006987 } } } } } } }