{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3548136353492737, "min": 0.3548136353492737, "max": 1.437155842781067, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10729.564453125, "min": 10729.564453125, "max": 43597.55859375, "count": 33 }, "Pyramids.Step.mean": { "value": 989937.0, "min": 29952.0, "max": 989937.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989937.0, "min": 29952.0, "max": 989937.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5821778774261475, "min": -0.10999443382024765, "max": 0.5862728953361511, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 163.59197998046875, "min": -26.398664474487305, "max": 163.59197998046875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0031980962958186865, "min": -0.0031980962958186865, "max": 0.307255357503891, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.8986650705337524, "min": -0.8986650705337524, "max": 72.81951904296875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0706158279040311, "min": 0.06668130365904376, "max": 0.07426039686325014, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0592374185604665, "min": 0.519822778042751, "max": 1.0592374185604665, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016114311801761184, "min": 0.0002257411502751245, "max": 0.01652999222667869, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24171467702641775, "min": 0.0024831526530263693, "max": 0.24171467702641775, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.49851750052667e-06, "min": 7.49851750052667e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011247776250790004, "min": 0.00011247776250790004, "max": 0.003331662089445999, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249947333333334, "min": 0.10249947333333334, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5374921000000001, "min": 1.3886848, "max": 2.4429655999999995, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002596973860000001, "min": 0.0002596973860000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003895460790000002, "min": 0.003895460790000002, "max": 0.1110643446, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010020655579864979, "min": 0.009695539250969887, "max": 0.3793948292732239, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15030983090400696, "min": 0.1357375532388687, "max": 2.655763864517212, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 319.1914893617021, "min": 319.1914893617021, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30004.0, "min": 15984.0, "max": 33062.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6382467889405312, "min": -1.0000000521540642, "max": 1.6382467889405312, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 153.99519816040993, "min": -31.99920167028904, "max": 153.99519816040993, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6382467889405312, "min": -1.0000000521540642, "max": 1.6382467889405312, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 153.99519816040993, "min": -31.99920167028904, "max": 153.99519816040993, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03313616113650533, "min": 0.03313616113650533, "max": 7.723539190366864, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1147991468315013, "min": 3.0726734301715624, "max": 123.57662704586983, "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": "1752537103", "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": "1752539253" }, "total": 2150.6781928339997, "count": 1, "self": 0.47665820799920766, "children": { "run_training.setup": { "total": 0.01974013200015179, "count": 1, "self": 0.01974013200015179 }, "TrainerController.start_learning": { "total": 2150.1817944940003, "count": 1, "self": 1.1863307380408514, "children": { "TrainerController._reset_env": { "total": 2.238081342999976, "count": 1, "self": 2.238081342999976 }, "TrainerController.advance": { "total": 2146.6825094529595, "count": 63823, "self": 1.2217102919544232, "children": { "env_step": { "total": 1505.9070702489685, "count": 63823, "self": 1369.9375211280542, "children": { "SubprocessEnvManager._take_step": { "total": 135.27357252792694, "count": 63823, "self": 4.206658380956014, "children": { "TorchPolicy.evaluate": { "total": 131.06691414697093, "count": 62555, "self": 131.06691414697093 } } }, "workers": { "total": 0.6959765929873356, "count": 63823, "self": 0.0, "children": { "worker_root": { "total": 2145.864868218004, "count": 63823, "is_parallel": true, "self": 878.7389334630454, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018956690000777598, "count": 1, "is_parallel": true, "self": 0.0005831769999531389, "children": { "_process_rank_one_or_two_observation": { "total": 0.001312492000124621, "count": 8, "is_parallel": true, "self": 0.001312492000124621 } } }, "UnityEnvironment.step": { "total": 0.045261617000051046, "count": 1, "is_parallel": true, "self": 0.0005287740000312624, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046912499988138734, "count": 1, "is_parallel": true, "self": 0.00046912499988138734 }, "communicator.exchange": { "total": 0.04269048100013606, "count": 1, "is_parallel": true, "self": 0.04269048100013606 }, "steps_from_proto": { "total": 0.0015732370000023366, "count": 1, "is_parallel": true, "self": 0.0003235279998534679, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012497090001488687, "count": 8, "is_parallel": true, "self": 0.0012497090001488687 } } } } } } }, "UnityEnvironment.step": { "total": 1267.1259347549587, "count": 63822, "is_parallel": true, "self": 30.616616865861715, "children": { "UnityEnvironment._generate_step_input": { "total": 21.7335735710235, "count": 63822, "is_parallel": true, "self": 21.7335735710235 }, "communicator.exchange": { "total": 1124.446934412025, "count": 63822, "is_parallel": true, "self": 1124.446934412025 }, "steps_from_proto": { "total": 90.32880990604849, "count": 63822, "is_parallel": true, "self": 17.422450531935965, "children": { "_process_rank_one_or_two_observation": { "total": 72.90635937411253, "count": 510576, "is_parallel": true, "self": 72.90635937411253 } } } } } } } } } } }, "trainer_advance": { "total": 639.5537289120366, "count": 63823, "self": 2.2862144629982595, "children": { "process_trajectory": { "total": 118.92398384703824, "count": 63823, "self": 118.73749086203748, "children": { "RLTrainer._checkpoint": { "total": 0.18649298500076839, "count": 2, "self": 0.18649298500076839 } } }, "_update_policy": { "total": 518.3435306020001, "count": 449, "self": 290.7988826939986, "children": { "TorchPPOOptimizer.update": { "total": 227.54464790800148, "count": 22818, "self": 227.54464790800148 } } } } } } }, "trainer_threads": { "total": 9.099999260797631e-07, "count": 1, "self": 9.099999260797631e-07 }, "TrainerController._save_models": { "total": 0.07487205000006725, "count": 1, "self": 0.0013757130000158213, "children": { "RLTrainer._checkpoint": { "total": 0.07349633700005143, "count": 1, "self": 0.07349633700005143 } } } } } } }