Skip to yearly menu bar Skip to main content


Poster

Exploration in Structured Reinforcement Learning

Jungseul Ok · Alexandre Proutiere · Damianos Tranos

Room 517 AB #160

Keywords: [ Bandit Algorithms ] [ Learning Theory ] [ Online Learning ] [ Reinforcement Learning and Planning ] [ Reinforcement Learning ] [ Markov Decision Processes ]


Abstract:

We address reinforcement learning problems with finite state and action spaces where the underlying MDP has some known structure that could be potentially exploited to minimize the exploration rates of suboptimal (state, action) pairs. For any arbitrary structure, we derive problem-specific regret lower bounds satisfied by any learning algorithm. These lower bounds are made explicit for unstructured MDPs and for those whose transition probabilities and average reward functions are Lipschitz continuous w.r.t. the state and action. For Lipschitz MDPs, the bounds are shown not to scale with the sizes S and A of the state and action spaces, i.e., they are smaller than c log T where T is the time horizon and the constant c only depends on the Lipschitz structure, the span of the bias function, and the minimal action sub-optimality gap. This contrasts with unstructured MDPs where the regret lower bound typically scales as SA log T. We devise DEL (Directed Exploration Learning), an algorithm that matches our regret lower bounds. We further simplify the algorithm for Lipschitz MDPs, and show that the simplified version is still able to efficiently exploit the structure.

Live content is unavailable. Log in and register to view live content