No?regret Learning in Dynamic Stackelberg Games.

📖 Description

No-Regret Learning in Dynamic Stackelberg Games Niklas Lauffer, Mahsa Ghasemi, Abolfazl Hashemi, Y agiz Savas, and Ufuk Topcu Abstract ? In a Stackelberg game , aleader commits to a randomized strategy, and a follower chooses their best strategy in response. We consider an extension of a stan- dard Stackelberg game, called a discrete-time dynamic Stackelberg game , that has an underlying state space that affects the leader?s rewards and available strategies and evolves in a Markovian manner depending on both the leader and follower?s selected strategies. Although stan- dard Stackelberg games have been utilized to improve scheduling in security domains, their deployment is often limited by requiring complete information of the follower?s utility function. In contrast, we consider scenarios where the follower?s utility function is unknown to the leader; how- ever, it can be linearly parameterized. Our objective then is to provide an algorithm that prescribes a randomized strategy to t...

📊 Game Impacts

💭 Reactions

🔗 Sources

• [1] https://arxiv.org/abs/2202.04786