Predictive State Representations with State Space Partitioning

• DOI: 10.5555/2772879.2773312
• Publication Date: 2015-05-04
• Authors: Yunlong Liu; Yun Tang; Yifeng Zeng

Predictive state representations (PSRs) are powerful methods of modeling dynamical systems by representing through observational data. Most the current PSR techniques focus on learning a complete model from entire space. Consequently, often not scalable due to dimensional curse, which limits applications PSR. In this paper, we propose new technique. Instead directly at one time, learn set local models each is constructed sub-state space and then combine learnt models. We employ landmark technique partition further show theoretical guarantees performance proposed present empirical results multiple domains.