Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Learning and Decision-Making with Strategic Feedback (StratML)

Exploration and Incentives in Reinforcement Learning

Max Simchowitz · Aleksandrs Slivkins


Abstract: How do you incentivize self-interested agents to $\text{\emph{explore}}$ when they prefer to $\text{\emph{exploit}}$? We consider complex exploration problems, where each agent faces the same (but unknown) MDP. In contrast with traditional formulations of reinforcement learning, agents control the choice of policies, whereas an algorithm can only issue recommendations. However, the algorithm controls the flow of information, and can incentivize the agents to explore via information asymmetry. We design an algorithm which explores all reachable states in the MDP. We achieve provable guarantees similar to those for incentivizing exploration in static, stateless exploration problems studied previously.

Chat is not available.