4 papers
Finite-time convergence to an -efficient Nash equilibrium in potential games
Anna Maddux, Reda Ouhamma, Maryam Kamgarpour
This paper investigates the convergence time of log-linear learning to an -efficient Nash equilibrium in potential games, where an efficient Nash equilibrium is defined as the…
Efficient Preference-Based Reinforcement Learning: Randomized Exploration Meets Experimental Design
Andreas Schlaginhaufen, Reda Ouhamma, Maryam Kamgarpour
We study reinforcement learning from human feedback in general Markov decision processes, where agents learn from trajectory-level preference comparisons. A central challenge in th…
Nash equilibria in scalar discrete-time linear quadratic games
Giulio Salizzoni, Reda Ouhamma, Maryam Kamgarpour
An open problem in linear quadratic (LQ) games has been characterizing the Nash equilibria. This problem has renewed relevance given the surge of work on understanding the converge…
Learning in Zero-Sum Markov Games: Relaxing Strong Reachability and Mixing Time Assumptions
Reda Ouhamma, Maryam Kamgarpour
We address payoff-based decentralized learning in infinite-horizon zero-sum Markov games. In this setting, each player makes decisions based solely on received rewards, without obs…