Temporally Extended Actions For Reinforcement Learning Based Schedulers

Temporally Extended Actions For Reinforcement Learning Based Schedulers

Prakhar Ojha, Siddhartha R Thota, Vani M and Mohit P Tahilianni National Institute of Technology Karnataka, India

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.

KEYWORDS Temporal Extension of Actions, Options, Reinforcement Learning, Online Machine Learning, Operating System, Scheduler, Preemption Original Source URL: http://aircconline.com/ijscai/V4N4/4415ijscai01.pdf http://airccse.org/journal/ijscai/current2015.html

Comments

Post a Comment

Popular posts from this blog

Cancer Prognosis Prediction Using Balanced Stratified Sampling

Cancer Prognosis Prediction Using Balanced Stratified Sampling J.S.Saleema1, N.Bhagawathi2, S.Monica2, P.Deepa Shenoy2, K.R.Venugopal2 and L.M.Patnaik3, 1Christ University, India 2University Visvesvaraya College of Engineering, India 3Indian Institute of Science, India ABSTRACT High accuracy in cancer prediction is important to improve the quality of the treatment and to improve the rate of survivability of patients. As the data volume is increasing rapidly in the healthcare research, the analytical challenge exists in double. The use of effective sampling technique in classification algorithms always yields good prediction accuracy. The SEER public use cancer database provides various prominent class labels for prognosis prediction. The main objective of this paper is to find the effect of sampling techniques in classifying the prognosis variable and propose an ideal sampling method based on the outcome of the experimentation. In the first phase of this work the traditional rando...
Read more

Design and Implementation of Smart Cooking Based on Amazon Echo

Design and Implementation of Smart Cooking Based on Amazon Echo Lin Xiaoguang1,2,3, Yang Yong3 and Zhang Ju1,3 1University of Chinese Academy of Sciences, China 2Chinese Academy of Sciences - Chengdu, China 3Chinese Academy of Sciences - Chongqing, China ABSTRACT Smart cooking based on Amazon Echo uses the internet of things and cloud computing to assist in cooking food. People may speak to Amazon Echo during the cooking in order to get the information and situation of the cooking. Amazon Echo recognizes what people say, then transfers the information to the cloud services, and speaks to people the results that cloud services make by querying the embedded cooking knowledge and achieving the information of intelligent kitchen devices online. An intelligent food thermometer and its mobile application are well-designed and implemented to monitor the temperature of cooking food. KEYWORDS Smart Cooking, Things of Internet, Cloud Services, Smart Home. Original Source URL: ht...
Read more