{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.25907325744628906, "min": 0.2558559775352478, "max": 1.3774148225784302, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7797.068359375, "min": 7671.5859375, "max": 41785.2578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989939.0, "min": 29952.0, "max": 989939.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989939.0, "min": 29952.0, "max": 989939.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5694802403450012, "min": -0.08090469241142273, "max": 0.6594760417938232, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 157.74603271484375, "min": -19.417125701904297, "max": 184.65328979492188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0013450278202071786, "min": -0.0013450278202071786, "max": 0.29711470007896423, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.37257272005081177, "min": -0.37257272005081177, "max": 72.1988754272461, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06787197015780423, "min": 0.0649626392140937, "max": 0.07350469485875996, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9502075822092592, "min": 0.48074426188705033, "max": 1.0884475505102753, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016698443145114216, "min": 0.0001354336807210731, "max": 0.017107737701982748, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23377820403159905, "min": 0.0016252041686528774, "max": 0.2566160655297412, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.320011845742859e-06, "min": 7.320011845742859e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010248016584040003, "min": 0.00010248016584040003, "max": 0.0036343240885587, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243997142857143, "min": 0.10243997142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341596, "min": 1.3886848, "max": 2.6114413000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025375314571428575, "min": 0.00025375314571428575, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00355254404, "min": 0.00355254404, "max": 0.12116298587000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0125659154728055, "min": 0.0125659154728055, "max": 0.4227711856365204, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17592281103134155, "min": 0.17592281103134155, "max": 2.9593982696533203, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 325.11578947368423, "min": 284.2962962962963, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30886.0, "min": 15984.0, "max": 34169.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5694273472616547, "min": -1.0000000521540642, "max": 1.6971814635175246, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 149.0955979898572, "min": -30.996401607990265, "max": 183.29559805989265, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5694273472616547, "min": -1.0000000521540642, "max": 1.6971814635175246, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 149.0955979898572, "min": -30.996401607990265, "max": 183.29559805989265, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04201130394940265, "min": 0.039980431873118505, "max": 8.555010987445712, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9910738751932513, "min": 3.8159166038094554, "max": 136.8801757991314, "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": "1705162879", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1705165193" }, "total": 2313.951981217001, "count": 1, "self": 0.5283461690014519, "children": { "run_training.setup": { "total": 0.046416883999881975, "count": 1, "self": 0.046416883999881975 }, "TrainerController.start_learning": { "total": 2313.3772181639997, "count": 1, "self": 1.3994488829239344, "children": { "TrainerController._reset_env": { "total": 1.9937093810003716, "count": 1, "self": 1.9937093810003716 }, "TrainerController.advance": { "total": 2309.907793514075, "count": 64136, "self": 1.5078189603264036, "children": { "env_step": { "total": 1657.7619630088566, "count": 64136, "self": 1520.9859004149175, "children": { "SubprocessEnvManager._take_step": { "total": 135.93726991313088, "count": 64136, "self": 4.865639828131862, "children": { "TorchPolicy.evaluate": { "total": 131.07163008499901, "count": 62570, "self": 131.07163008499901 } } }, "workers": { "total": 0.8387926808081829, "count": 64136, "self": 0.0, "children": { "worker_root": { "total": 2308.1251556189873, "count": 64136, "is_parallel": true, "self": 910.4233566200446, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017680569999356521, "count": 1, "is_parallel": true, "self": 0.0005607580005744239, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012072989993612282, "count": 8, "is_parallel": true, "self": 0.0012072989993612282 } } }, "UnityEnvironment.step": { "total": 0.05598966700017627, "count": 1, "is_parallel": true, "self": 0.0006721680010741693, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000526946999343636, "count": 1, "is_parallel": true, "self": 0.000526946999343636 }, "communicator.exchange": { "total": 0.05299489899971377, "count": 1, "is_parallel": true, "self": 0.05299489899971377 }, "steps_from_proto": { "total": 0.0017956530000446946, "count": 1, "is_parallel": true, "self": 0.0003733340008693631, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014223189991753316, "count": 8, "is_parallel": true, "self": 0.0014223189991753316 } } } } } } }, "UnityEnvironment.step": { "total": 1397.7017989989426, "count": 64135, "is_parallel": true, "self": 36.033980790237365, "children": { "UnityEnvironment._generate_step_input": { "total": 26.385682583930247, "count": 64135, "is_parallel": true, "self": 26.385682583930247 }, "communicator.exchange": { "total": 1230.2112378638703, "count": 64135, "is_parallel": true, "self": 1230.2112378638703 }, "steps_from_proto": { "total": 105.0708977609047, "count": 64135, "is_parallel": true, "self": 21.16046945015114, "children": { "_process_rank_one_or_two_observation": { "total": 83.91042831075356, "count": 513080, "is_parallel": true, "self": 83.91042831075356 } } } } } } } } } } }, "trainer_advance": { "total": 650.6380115448919, "count": 64136, "self": 2.6976854837885185, "children": { "process_trajectory": { "total": 130.95859657608617, "count": 64136, "self": 130.78086773008636, "children": { "RLTrainer._checkpoint": { "total": 0.17772884599980898, "count": 2, "self": 0.17772884599980898 } } }, "_update_policy": { "total": 516.9817294850172, "count": 457, "self": 300.25484848103406, "children": { "TorchPPOOptimizer.update": { "total": 216.72688100398318, "count": 22788, "self": 216.72688100398318 } } } } } } }, "trainer_threads": { "total": 1.2900000001536682e-06, "count": 1, "self": 1.2900000001536682e-06 }, "TrainerController._save_models": { "total": 0.07626509600049758, "count": 1, "self": 0.001152857999841217, "children": { "RLTrainer._checkpoint": { "total": 0.07511223800065636, "count": 1, "self": 0.07511223800065636 } } } } } } }