Online feature selection for model-based reinforcement learning
Conference Proceeding Article
We propose a new framework for learning the world dynamics of feature-rich environments in model-based reinforcement learning. The main idea is formalized as a new, factored state-transition representation that supports efficient online-learning of the relevant features. We construct the transition models through predicting how the actions change the world. We introduce an online sparse coding learning technique for feature selection in high-dimensional spaces. We derive theoretical guarantees for our framework and empirically demonstrate its practicality in both simulated and real robotics domains. Copyright 2013 by the author(s).
Artificial intelligence; Software engineering High dimensional spaces, Learning techniques, Model-based reinforcement learning, Online feature selection, Relevant features, Theoretical guarantees, Transition model, World dynamics
Databases and Information Systems
Data Management and Analytics
Proceedings of The 30th International Conference on Machine Learning
International Machine Learning Society (IMLS)
City or Country
Nguyen, Trung Thanh; Li, Zhuoru; Silander, Tomi; and Tze-Yun LEONG.
Online feature selection for model-based reinforcement learning. (2013). Proceedings of The 30th International Conference on Machine Learning. 1, 498-506. Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/3030