@article{Ma_Pineau_2015, title={Information Gathering and Reward Exploitation of Subgoals for POMDPs}, volume={29}, url={https://ojs.aaai.org/index.php/AAAI/article/view/9659}, DOI={10.1609/aaai.v29i1.9659}, abstractNote={ <p> Planning in large partially observable Markov decision processes (POMDPs) is challenging especially when a long planning horizon is required. A few recent algorithms successfully tackle this case but at the expense of a weaker information-gathering capacity. In this paper, we propose Information Gathering and Reward Exploitation of Subgoals (IGRES), a randomized POMDP planning algorithm that leverages information in the state space to automatically generate "macro-actions" to tackle tasks with long planning horizons, while locally exploring the belief space to allow effective information gathering. Experimental results show that IGRES is an effective multi-purpose POMDP solver, providing state-of-the-art performance for both long horizon planning tasks and information-gathering tasks on benchmark domains. Additional experiments with an ecological adaptive management problem indicate that IGRES is a promising tool for POMDP planning in real-world settings. </p> }, number={1}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Ma, Hang and Pineau, Joelle}, year={2015}, month={Mar.} }