{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.13560117781162262, "min": 0.13368962705135345, "max": 1.501430869102478, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4048.5087890625, "min": 4008.5498046875, "max": 45547.40625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999973.0, "min": 29952.0, "max": 2999973.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999973.0, "min": 29952.0, "max": 2999973.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7644326686859131, "min": -0.19673281908035278, "max": 0.8736488223075867, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 223.97877502441406, "min": -46.62567901611328, "max": 265.5892333984375, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.002483826130628586, "min": -0.05445689335465431, "max": 0.3073934018611908, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.7277610301971436, "min": -14.213249206542969, "max": 73.7744140625, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06763423736611869, "min": 0.06346013113171192, "max": 0.07350707741127172, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9468793231256616, "min": 0.49063711318782205, "max": 1.0903543142131622, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01449084068909066, "min": 0.0007678637709816031, "max": 0.015381792040488127, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20287176964726922, "min": 0.005375046396871222, "max": 0.22169910624506886, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.486370933147619e-06, "min": 1.486370933147619e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0809193064066667e-05, "min": 2.0809193064066667e-05, "max": 0.003969988976670366, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049542380952381, "min": 0.10049542380952381, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4069359333333333, "min": 1.3897045333333333, "max": 2.782490266666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.9492838571428556e-05, "min": 5.9492838571428556e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008328997399999998, "min": 0.0008328997399999998, "max": 0.13234063037000002, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008348598144948483, "min": 0.008327372372150421, "max": 0.4501631557941437, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1168803796172142, "min": 0.1165832132101059, "max": 3.151142120361328, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 239.47154471544715, "min": 210.07692307692307, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29455.0, "min": 15984.0, "max": 33473.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7605284459707213, "min": -1.0000000521540642, "max": 1.789923059565204, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 216.54499885439873, "min": -32.000001668930054, "max": 255.95899751782417, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7605284459707213, "min": -1.0000000521540642, "max": 1.789923059565204, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 216.54499885439873, "min": -32.000001668930054, "max": 255.95899751782417, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02104058663069263, "min": 0.018813573361608084, "max": 8.40426024980843, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.5879921555751935, "min": 2.4167374351236504, "max": 134.4681639969349, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1745425580", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1745432684" }, "total": 7104.38572041, "count": 1, "self": 0.4759001120000903, "children": { "run_training.setup": { "total": 0.020798721000119258, "count": 1, "self": 0.020798721000119258 }, "TrainerController.start_learning": { "total": 7103.889021577001, "count": 1, "self": 3.877247766306027, "children": { "TrainerController._reset_env": { "total": 2.795401811999909, "count": 1, "self": 2.795401811999909 }, "TrainerController.advance": { "total": 7097.131083445696, "count": 194791, "self": 4.141419890712314, "children": { "env_step": { "total": 5042.979808160014, "count": 194791, "self": 4604.351119860961, "children": { "SubprocessEnvManager._take_step": { "total": 436.414859180848, "count": 194791, "self": 13.392487223245553, "children": { "TorchPolicy.evaluate": { "total": 423.02237195760245, "count": 187552, "self": 423.02237195760245 } } }, "workers": { "total": 2.213829118204103, "count": 194791, "self": 0.0, "children": { "worker_root": { "total": 7089.1628429810235, "count": 194791, "is_parallel": true, "self": 2816.293452051209, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002276563000123133, "count": 1, "is_parallel": true, "self": 0.0007601870001963107, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015163759999268223, "count": 8, "is_parallel": true, "self": 0.0015163759999268223 } } }, "UnityEnvironment.step": { "total": 0.07325522799965256, "count": 1, "is_parallel": true, "self": 0.0005448509996313078, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004579239998747653, "count": 1, "is_parallel": true, "self": 0.0004579239998747653 }, "communicator.exchange": { "total": 0.07060592400011956, "count": 1, "is_parallel": true, "self": 0.07060592400011956 }, "steps_from_proto": { "total": 0.0016465290000269306, "count": 1, "is_parallel": true, "self": 0.0003471469999567489, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012993820000701817, "count": 8, "is_parallel": true, "self": 0.0012993820000701817 } } } } } } }, "UnityEnvironment.step": { "total": 4272.8693909298145, "count": 194790, "is_parallel": true, "self": 93.72713600207862, "children": { "UnityEnvironment._generate_step_input": { "total": 68.88139424126484, "count": 194790, "is_parallel": true, "self": 68.88139424126484 }, "communicator.exchange": { "total": 3826.798722410338, "count": 194790, "is_parallel": true, "self": 3826.798722410338 }, "steps_from_proto": { "total": 283.4621382761329, "count": 194790, "is_parallel": true, "self": 56.92660307803908, "children": { "_process_rank_one_or_two_observation": { "total": 226.53553519809384, "count": 1558320, "is_parallel": true, "self": 226.53553519809384 } } } } } } } } } } }, "trainer_advance": { "total": 2050.00985539497, "count": 194791, "self": 7.963267833209102, "children": { "process_trajectory": { "total": 388.9966199337573, "count": 194791, "self": 388.45569495675636, "children": { "RLTrainer._checkpoint": { "total": 0.540924977000941, "count": 6, "self": 0.540924977000941 } } }, "_update_policy": { "total": 1653.0499676280037, "count": 1400, "self": 923.5317362758651, "children": { "TorchPPOOptimizer.update": { "total": 729.5182313521386, "count": 68382, "self": 729.5182313521386 } } } } } } }, "trainer_threads": { "total": 8.90999217517674e-07, "count": 1, "self": 8.90999217517674e-07 }, "TrainerController._save_models": { "total": 0.08528766199924576, "count": 1, "self": 0.0011114230001112446, "children": { "RLTrainer._checkpoint": { "total": 0.08417623899913451, "count": 1, "self": 0.08417623899913451 } } } } } } }