{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.22112534940242767, "min": 0.22112534940242767, "max": 1.480122447013855, "count": 44 }, "Pyramids.Policy.Entropy.sum": { "value": 6527.6201171875, "min": 6527.6201171875, "max": 44900.99609375, "count": 44 }, "Pyramids.Step.mean": { "value": 1319918.0, "min": 29952.0, "max": 1319918.0, "count": 44 }, "Pyramids.Step.sum": { "value": 1319918.0, "min": 29952.0, "max": 1319918.0, "count": 44 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6153923869132996, "min": -0.08644306659698486, "max": 0.7104189991950989, "count": 44 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 169.23291015625, "min": -20.832778930664062, "max": 206.73580932617188, "count": 44 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.017557211220264435, "min": 0.0017114699585363269, "max": 0.47905588150024414, "count": 44 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.828233242034912, "min": 0.49974924325942993, "max": 113.53624725341797, "count": 44 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06841072260997155, "min": 0.06504284059753575, "max": 0.07371400642134776, "count": 44 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0261608391495733, "min": 0.49088822811207705, "max": 1.0945098796316113, "count": 44 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01419901789392016, "min": 0.0010947507362378494, "max": 0.017648000888422957, "count": 44 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2129852684088024, "min": 0.007663255153664945, "max": 0.26472001332634437, "count": 44 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00016950170349944665, "min": 0.00016950170349944665, "max": 0.00029838354339596195, "count": 44 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0025425255524917, "min": 0.0020691136102954665, "max": 0.004117548927483733, "count": 44 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.15650055333333335, "min": 0.15650055333333335, "max": 0.19946118095238097, "count": 44 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.3475083000000003, "min": 1.3897045333333333, "max": 2.8725162666666675, "count": 44 }, "Pyramids.Policy.Beta.mean": { "value": 0.005654405278, "min": 0.005654405278, "max": 0.009946171977142856, "count": 44 }, "Pyramids.Policy.Beta.sum": { "value": 0.08481607917, "min": 0.06897148288, "max": 0.13726437504, "count": 44 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010335207916796207, "min": 0.010335207916796207, "max": 0.4952378273010254, "count": 44 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15502811968326569, "min": 0.1518491804599762, "max": 3.4666647911071777, "count": 44 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 346.14444444444445, "min": 280.651376146789, "max": 999.0, "count": 44 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31153.0, "min": 15984.0, "max": 32563.0, "count": 44 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.542713312142425, "min": -1.0000000521540642, "max": 1.6864234100322466, "count": 44 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 138.84419809281826, "min": -32.000001668930054, "max": 187.19299851357937, "count": 44 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.542713312142425, "min": -1.0000000521540642, "max": 1.6864234100322466, "count": 44 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 138.84419809281826, "min": -32.000001668930054, "max": 187.19299851357937, "count": 44 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03730699013847495, "min": 0.03140115741939758, "max": 9.7479402218014, "count": 44 }, "Pyramids.Policy.RndReward.sum": { "value": 3.357629112462746, "min": 3.327852823509602, "max": 155.9670435488224, "count": 44 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 44 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 44 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1744118307", "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 Training2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1744121606" }, "total": 3298.9114448860005, "count": 1, "self": 0.5754334870002822, "children": { "run_training.setup": { "total": 0.020665155999950002, "count": 1, "self": 0.020665155999950002 }, "TrainerController.start_learning": { "total": 3298.315346243, "count": 1, "self": 2.068192744908629, "children": { "TrainerController._reset_env": { "total": 3.2834365140001864, "count": 1, "self": 3.2834365140001864 }, "TrainerController.advance": { "total": 3292.963658989091, "count": 85222, "self": 2.18317593382244, "children": { "env_step": { "total": 2327.4699649682007, "count": 85222, "self": 2105.386245216022, "children": { "SubprocessEnvManager._take_step": { "total": 220.89795684411638, "count": 85222, "self": 6.66124266113161, "children": { "TorchPolicy.evaluate": { "total": 214.23671418298477, "count": 82938, "self": 214.23671418298477 } } }, "workers": { "total": 1.1857629080620882, "count": 85221, "self": 0.0, "children": { "worker_root": { "total": 3291.1892943330936, "count": 85221, "is_parallel": true, "self": 1349.0991235771346, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005332671999894956, "count": 1, "is_parallel": true, "self": 0.003825249999636071, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015074220002588845, "count": 8, "is_parallel": true, "self": 0.0015074220002588845 } } }, "UnityEnvironment.step": { "total": 0.050107941000078426, "count": 1, "is_parallel": true, "self": 0.0005287619999307935, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004568699998799275, "count": 1, "is_parallel": true, "self": 0.0004568699998799275 }, "communicator.exchange": { "total": 0.04727190200014775, "count": 1, "is_parallel": true, "self": 0.04727190200014775 }, "steps_from_proto": { "total": 0.001850407000119958, "count": 1, "is_parallel": true, "self": 0.0003605230001539894, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014898839999659685, "count": 8, "is_parallel": true, "self": 0.0014898839999659685 } } } } } } }, "UnityEnvironment.step": { "total": 1942.090170755959, "count": 85220, "is_parallel": true, "self": 45.43887072929465, "children": { "UnityEnvironment._generate_step_input": { "total": 32.01485306692575, "count": 85220, "is_parallel": true, "self": 32.01485306692575 }, "communicator.exchange": { "total": 1729.5269682758226, "count": 85220, "is_parallel": true, "self": 1729.5269682758226 }, "steps_from_proto": { "total": 135.109478683916, "count": 85220, "is_parallel": true, "self": 27.86022681283248, "children": { "_process_rank_one_or_two_observation": { "total": 107.24925187108352, "count": 681760, "is_parallel": true, "self": 107.24925187108352 } } } } } } } } } } }, "trainer_advance": { "total": 963.3105180870677, "count": 85221, "self": 4.055906078209546, "children": { "process_trajectory": { "total": 183.44610193585413, "count": 85221, "self": 183.0872225678545, "children": { "RLTrainer._checkpoint": { "total": 0.35887936799963427, "count": 2, "self": 0.35887936799963427 } } }, "_update_policy": { "total": 775.8085100730041, "count": 608, "self": 425.17458344692363, "children": { "TorchPPOOptimizer.update": { "total": 350.63392662608044, "count": 30162, "self": 350.63392662608044 } } } } } } }, "trainer_threads": { "total": 1.2909995348309167e-06, "count": 1, "self": 1.2909995348309167e-06 }, "TrainerController._save_models": { "total": 5.670400059898384e-05, "count": 1, "self": 1.9136000446451362e-05, "children": { "RLTrainer._checkpoint": { "total": 3.756800015253248e-05, "count": 1, "self": 3.756800015253248e-05 } } } } } } }