Multi-resolution Exploration in Continuous Spaces

The essence of exploration is acting to try to decrease uncertainty. We propose a new methodology for representing uncertainty in continuous-state control problems. Our approach, multi-resolution exploration (MRE), uses a hierarchical mapping to identify regions of the state space that would benefit from additional samples. We demonstrate MRE's broad utility by using it to speed up learning in a prototypical model-based and value-based reinforcement-learning method. Empirical results show that MRE improves upon state-of-the-art exploration approaches.

• Type: Conference
• Year: 2008
• Where: NIPS
• Authors: Ali Nouri, Michael L. Littman
• Keywords: Exploration, Information Technology, MRE's Broad Utility, NIPS 2008, State-of-the-art Exploration Approaches