MDP modeling for multi-stage stochastic programs

arXiv:2509.22981v2 Announce Type: replace Abstract: We study a class of multi-stage stochastic programs, which incorporate modeling features from Markov decision processes (MDPs). This class includes structured MDPs with continuous action and state spaces. We extend policy graphs to include decision-dependent uncertainty for one-step transition probabilities as well as a limited form of statistical learning. We focus on the expressiveness of our modeling approach, illustrating ideas with a series of examples of increasing complexity. As a solution method, we develop new variants of stochastic dual dynamic programming, including approximations to handle non-convexities.

Related

• Beyond Pessimism: Offline Learning in KL-regularized Games
• The Theorems of Dr. David Blackwell and Their Contributions to Artificial Intelligence
• Multi-agent Reach-avoid MDP via Potential Games and Low-rank Policy Structure

Source: arXiv cs.LG | 2026-04-10