In this letter, we consider the application of max-plus-linear approximators for Q-function in offline reinforcement learning of discounted Markov decision processes. In particular, we incorporate ...

Comparing Modeling Approaches for Distributed Contested Logistics. American Journal of Operations Research, 15, 125-145. doi: ...

Your Buyers’ Search Behavior Has Changed Search used to be straightforward: A buyer typed in a query, scanned a results page, and clicked through to vendor content. But that linear search-to ...

The simultaneous policy update algorithm (SPUA) has been extensively studied for linear zero-sum games due to its efficient single-loop iteration. However, selecting an appropriate initial matrix for ...