Weina Wang

We use a novel projection-based Lyapunov function to prove the first asymptotic optimality theorem for fully heterogeneous weakly-coupled Markov Decision Processes.

We propose a Stochastic-Programming-based (SP-based) policy for finite-horizon RMABs that achieves an optimality gap of $\tilde{\mathcal{O}}(1/N)$, addressing the limitations of Linear-Programming-based (LP-based) policies in degenerate settings.