Paper Session V

• Seiji Shaw, Travis Manderson, Chad Kessens, and Nicholas Roy, “Toward Learning POMDPs Beyond Full-Rank Actions and State Observability”
• Aral Köse, Vadim Weinstein, and Steven LaValle, “What a Fool Believes: Characterizing Plausible Environments from Weak Sensing Histories”
• Mohamad Louai Shehab, Antoine Aspeel, and Necmiye Ozay, “Active Reward Machine Inference From Raw State Trajectories”
• Da Kong and Vadim Indelman, “Open-loop POMDP Simplification and Safe Skipping of Replanning with Formal Performance Guarantees”