3 papers
cs.CV2026
Exploring the AI Obedience: Why is Generating a Pure Color Image Harder than CyberPunk?
Hongyu Li, Kuan Liu, Yuan Chen +6
Recent advances in generative AI have shown human-level performance in complex content creation. However, we identify a "Paradox of Simplicity": models that can render complex scen…
cs.GT2026
Characterizing Robustness of Strategies to Novelty in Zero-Sum Open Worlds
Mayank Kejriwal, Shilpa Thomas, Hongyu Li
In open-world environments, artificial agents must often contend with novel conditions that deviate from their training or design assumptions. This paper studies the robustness of…
cs.LG2021
Decision Making in Monopoly using a Hybrid Deep Reinforcement Learning Approach
Trevor Bonjour, Marina Haliem, Aala Alsalem +5
Learning to adapt and make real-time informed decisions in a dynamic and complex environment is a challenging problem. Monopoly is a popular strategic board game that requires play…