Near-Optimal BRL using Optimistic Local Transitions
Araya, Mauricio, Buffet, Olivier, Thomas, Vincent
–arXiv.org Artificial Intelligence
Model-based Bayesian Reinforcement Learning (BRL) allows a found formalization of the problem of acting optimally while facing an unknown environment, i.e., avoiding the exploration-exploitation dilemma. However, algorithms explicitly addressing BRL suffer from such a combinatorial explosion that a large body of work relies on heuristic algorithms. This paper introduces BOLT, a simple and (almost) deterministic heuristic algorithm for BRL which is optimistic about the transition function. We analyze BOLT's sample complexity, and show that under certain parameters, the algorithm is near-optimal in the Bayesian sense with high probability. Then, experimental results highlight the key differences of this method compared to previous work.
arXiv.org Artificial Intelligence
Jun-18-2012
- Country:
- North America > United States
- Massachusetts (0.14)
- Europe > United Kingdom
- Scotland (0.14)
- North America > United States
- Genre:
- Research Report (0.82)