%0 Journal Article %1 ojhatemporally %A Ojha, Prakhar %A Thota, Siddhartha R %A M, Vani %A Tahilianni, Mohit P %D 2015 %J International Journal on Soft Computing, Artificial Intelligence and Applications (IJSCAI) %K Actions Extension Learning Machine Online Operating Options Preemption Reinforcement Scheduler System Temporal of %N 3/4 %P 01 - 18 %T TEMPORALLY EXTENDED ACTIONS FOR REINFORCEMENT LEARNING BASED SCHEDULERS %U https://aircconline.com/ijscai/V4N4/4415ijscai01.pdf %V 4 %X Temporally extended actions have been proved to enhance the performance of reinforcement learning agents. The broader framework of ‘Options’ gives us a flexible way of representing such extended course of action in Markov decision processes. In this work we try to adapt options framework to model an operating system scheduler, which is expected not to allow processor stay idle if there is any process ready or waiting for its execution. A process is allowed to utilize CPU resources for a fixed quantum of time (timeslice) and subsequent context switch leads to considerable overhead. In this work we try to utilize the historical performances of a scheduler and try to reduce the number of redundant context switches. We propose a machine-learning module, based on temporally extended reinforcement-learning agent, to predict a better performing timeslice. We measure the importance of states, in option framework, by evaluating the impact of their absence and propose an algorithm to identify such checkpoint states. We present empirical evaluation of our approach in a maze-world navigation and their implications on ädaptive timeslice parameter" show efficient throughput time.

@article{ojhatemporally, abstract = {Temporally extended actions have been proved to enhance the performance of reinforcement learning agents. The broader framework of ‘Options’ gives us a flexible way of representing such extended course of action in Markov decision processes. In this work we try to adapt options framework to model an operating system scheduler, which is expected not to allow processor stay idle if there is any process ready or waiting for its execution. A process is allowed to utilize CPU resources for a fixed quantum of time (timeslice) and subsequent context switch leads to considerable overhead. In this work we try to utilize the historical performances of a scheduler and try to reduce the number of redundant context switches. We propose a machine-learning module, based on temporally extended reinforcement-learning agent, to predict a better performing timeslice. We measure the importance of states, in option framework, by evaluating the impact of their absence and propose an algorithm to identify such checkpoint states. We present empirical evaluation of our approach in a maze-world navigation and their implications on "adaptive timeslice parameter" show efficient throughput time.}, added-at = {2022-02-01T08:35:19.000+0100}, author = {Ojha, Prakhar and Thota, Siddhartha R and M, Vani and Tahilianni, Mohit P}, biburl = {https://www.bibsonomy.org/bibtex/2dc4b51b7df83dfc98b70f2be02c9d84d/leninsha}, interhash = {b37db1879e7dbd86c3b81b0f0ebc2005}, intrahash = {dc4b51b7df83dfc98b70f2be02c9d84d}, journal = {International Journal on Soft Computing, Artificial Intelligence and Applications (IJSCAI)}, keywords = {Actions Extension Learning Machine Online Operating Options Preemption Reinforcement Scheduler System Temporal of}, month = {November}, number = {3/4}, pages = {01 - 18}, timestamp = {2022-02-01T08:35:19.000+0100}, title = {TEMPORALLY EXTENDED ACTIONS FOR REINFORCEMENT LEARNING BASED SCHEDULERS }, url = {https://aircconline.com/ijscai/V4N4/4415ijscai01.pdf}, volume = 4, year = 2015 }