On Bits and Bandits: Quantifying the Regret-Information Trade-off

no code implementations • 26 May 2024 • Itai Shufaro, Nadav Merlis, Nir Weinberger, Shie Mannor

Using this setting, we introduce the first Bayesian regret lower bounds that depend on the information an agent accumulates.

On the Global Convergence of Policy Gradient in Average Reward Markov Decision Processes

no code implementations • 11 Mar 2024 • Navdeep Kumar, Yashaswini Murthy, Itai Shufaro, Kfir Y. Levy, R. Srikant, Shie Mannor

We present the first finite time global convergence analysis of policy gradient in the context of infinite horizon average reward Markov decision processes (MDPs).