Statistics – Machine Learning
Scientific paper
2009-02-02
Statistics
Machine Learning
13 pages, 1 figure. Slightly extended and corrected version (notation errors and lower bound calculation) of homonymous paper
Scientific paper
Research in reinforcement learning has produced algorithms for optimal decision making under uncertainty that fall within two main types. The first employs a Bayesian framework, where optimality improves with increased computational time. This is because the resulting planning task takes the form of a dynamic programming problem on a belief tree with an infinite number of states. The second type employs relatively simple algorithm which are shown to suffer small regret within a distribution-free framework. This paper presents a lower bound and a high probability upper bound on the optimal value function for the nodes in the Bayesian belief tree, which are analogous to similar bounds in POMDPs. The bounds are then used to create more efficient strategies for exploring the tree. The resulting algorithms are compared with the distribution-free algorithm UCB1, as well as a simpler baseline algorithm on multi-armed bandit problems.
No associations
LandOfFree
Tree Exploration for Bayesian RL Exploration does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Tree Exploration for Bayesian RL Exploration, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Tree Exploration for Bayesian RL Exploration will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-296440