{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6407908797264099, "min": 0.6130929589271545, "max": 1.5312467813491821, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19336.505859375, "min": 18500.693359375, "max": 46451.90234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989938.0, "min": 29952.0, "max": 989938.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989938.0, "min": 29952.0, "max": 989938.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3619399666786194, "min": -0.09999313205480576, "max": 0.3798351287841797, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 95.91409301757812, "min": -23.99835205078125, "max": 101.03614807128906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.028901921585202217, "min": -0.04035017266869545, "max": 0.4920494854450226, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.6590094566345215, "min": -10.571744918823242, "max": 118.58392333984375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.04795322648853818, "min": 0.04371030364806454, "max": 0.052553935559747814, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.33567258541976724, "min": 0.1986678668581222, "max": 0.4204314844779825, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012148024591927726, "min": 0.0015516333879625342, "max": 0.01565690283730094, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.08503617214349408, "min": 0.010077365402512214, "max": 0.10959831986110657, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.32888327135714e-06, "min": 7.32888327135714e-06, "max": 0.00029544960151679995, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 5.130218289949998e-05, "min": 5.130218289949998e-05, "max": 0.0018200388933203998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244292857142857, "min": 0.10244292857142857, "max": 0.1984832, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.7171005, "min": 0.7171005, "max": 1.3480908, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025404856428571423, "min": 0.00025404856428571423, "max": 0.00984847168, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0017783399499999998, "min": 0.0017783399499999998, "max": 0.06067729204, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014260482974350452, "min": 0.014260482974350452, "max": 0.6602411270141602, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09982337802648544, "min": 0.09982337802648544, "max": 2.6409645080566406, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 494.95238095238096, "min": 428.741935483871, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31182.0, "min": 15984.0, "max": 34183.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2827428368821976, "min": -1.0000000521540642, "max": 1.4421773949457752, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 80.81279872357845, "min": -30.323001712560654, "max": 89.41499848663807, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2827428368821976, "min": -1.0000000521540642, "max": 1.4421773949457752, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 80.81279872357845, "min": -30.323001712560654, "max": 89.41499848663807, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07264001584068562, "min": 0.07264001584068562, "max": 11.207279590889812, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.576320997963194, "min": 4.576320997963194, "max": 179.31647345423698, "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": "1775119907", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1775121774" }, "total": 1866.8951885662973, "count": 1, "self": 0.3768097050487995, "children": { "run_training.setup": { "total": 0.029470190405845642, "count": 1, "self": 0.029470190405845642 }, "TrainerController.start_learning": { "total": 1866.4889086708426, "count": 1, "self": 1.286378163844347, "children": { "TrainerController._reset_env": { "total": 2.767692819237709, "count": 1, "self": 2.767692819237709 }, "TrainerController.advance": { "total": 1862.3417597450316, "count": 63489, "self": 1.302156887948513, "children": { "env_step": { "total": 1170.1128269173205, "count": 63489, "self": 1007.3698288351297, "children": { "SubprocessEnvManager._take_step": { "total": 161.91519866511226, "count": 63489, "self": 4.364655204117298, "children": { "TorchPolicy.evaluate": { "total": 157.55054346099496, "count": 62565, "self": 157.55054346099496 } } }, "workers": { "total": 0.827799417078495, "count": 63489, "self": 0.0, "children": { "worker_root": { "total": 1864.4199082665145, "count": 63489, "is_parallel": true, "self": 961.1930472254753, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022834837436676025, "count": 1, "is_parallel": true, "self": 0.0006682351231575012, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016152486205101013, "count": 8, "is_parallel": true, "self": 0.0016152486205101013 } } }, "UnityEnvironment.step": { "total": 0.03531961888074875, "count": 1, "is_parallel": true, "self": 0.0003156997263431549, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00035895034670829773, "count": 1, "is_parallel": true, "self": 0.00035895034670829773 }, "communicator.exchange": { "total": 0.033449042588472366, "count": 1, "is_parallel": true, "self": 0.033449042588472366 }, "steps_from_proto": { "total": 0.0011959262192249298, "count": 1, "is_parallel": true, "self": 0.00027518346905708313, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009207427501678467, "count": 8, "is_parallel": true, "self": 0.0009207427501678467 } } } } } } }, "UnityEnvironment.step": { "total": 903.2268610410392, "count": 63488, "is_parallel": true, "self": 21.326674319803715, "children": { "UnityEnvironment._generate_step_input": { "total": 17.64187501370907, "count": 63488, "is_parallel": true, "self": 17.64187501370907 }, "communicator.exchange": { "total": 790.02005392313, "count": 63488, "is_parallel": true, "self": 790.02005392313 }, "steps_from_proto": { "total": 74.23825778439641, "count": 63488, "is_parallel": true, "self": 15.884524334222078, "children": { "_process_rank_one_or_two_observation": { "total": 58.35373345017433, "count": 507904, "is_parallel": true, "self": 58.35373345017433 } } } } } } } } } } }, "trainer_advance": { "total": 690.9267759397626, "count": 63489, "self": 2.009344857186079, "children": { "process_trajectory": { "total": 150.8905594572425, "count": 63489, "self": 150.6665277481079, "children": { "RLTrainer._checkpoint": { "total": 0.2240317091345787, "count": 2, "self": 0.2240317091345787 } } }, "_update_policy": { "total": 538.026871625334, "count": 232, "self": 379.49803598225117, "children": { "TorchPPOOptimizer.update": { "total": 158.52883564308286, "count": 11478, "self": 158.52883564308286 } } } } } } }, "trainer_threads": { "total": 9.57399606704712e-07, "count": 1, "self": 9.57399606704712e-07 }, "TrainerController._save_models": { "total": 0.09307698532938957, "count": 1, "self": 0.0011830590665340424, "children": { "RLTrainer._checkpoint": { "total": 0.09189392626285553, "count": 1, "self": 0.09189392626285553 } } } } } } }