4 papers
Robustness Analysis of POMDP Policies to Observation Perturbations
Benjamin Kraske, Qi Heng Ho, Federico Rossi +2
Policies for Partially Observable Markov Decision Processes (POMDPs) are often designed using a nominal system model. In practice, this model can deviate from the true system durin…
Learning Decentralized Routing Policies via Graph Attention-based Multi-Agent Reinforcement Learning in Lunar Delay-Tolerant Networks
Federico Lozano-Cuadra, Beatriz Soret, Marc Sanchez Net +2
We present a fully decentralized routing framework for multi-robot exploration missions operating under the constraints of a Lunar Delay-Tolerant Network (LDTN). In this setting, a…
Sound Heuristic Search Value Iteration for Undiscounted POMDPs with Reachability Objectives
Qi Heng Ho, Martin S. Feather, Federico Rossi +2
Partially Observable Markov Decision Processes (POMDPs) are powerful models for sequential decision making under transition and observation uncertainties. This paper studies the ch…
Recursively-Constrained Partially Observable Markov Decision Processes
Qi Heng Ho, Tyler Becker, Benjamin Kraske +5
Many sequential decision problems involve optimizing one objective function while imposing constraints on other objectives. Constrained Partially Observable Markov Decision Process…