Minimax PAC Bounds for Learning in Exogenous Contextual MDPs (opens in new tab)

We study PAC learning in tabular discounted Markov decision processes with exogenous i.i.d. contexts, with discount factor $\gamma$, finite state space $\mathcal X$, action space $\mathcal A$, and context space $\mathcal Z$. At each time step, a context is drawn independently from an unknown distribution $\mu$ and revealed before the agent acts. This context may affect both rewards and transitions, while remaining uncontrolled by the agent. Depe...