Blog

This page contains blog posts from students and researchers in the ADCL and DMU++ course.

DMU++ 2025 Student Posts

• Communication Lessons from Combat Aviation for Unmanned Wingmen - Mark Boyer
• Zero to Reality: AlphaGo, MuZero and the Road to Real-World AI - Lorenzzo Quevedo Mantovani
• Generative Models hate this one trick to mitigate Observation Complexity - Gabriel Agostine
• The Future of Safe RLHF (Reinforcement Learning from Human Feedback)
• Diffusion Models: A New Playground for Reinforcement Learning - Anaïs Cheval
• When Will Robots Do My Chores? Progress and Promises in Bridging Simulation and Reality - Xavier O’keefe
• Robust Trajectory RL - Daniel Huterer Prats
• What are the various ways of finding a lost child in a music festival efficiently? - Kelvin Aladum
• Oh, You Blockhead: Why Generalist Transformers Fail at Learning World Models - Ryan Draves
• No Confusion: Discrete Diffusion - Sean Campbell
• Some Background Diffusion Math - Sean Campbell
• Soft Actor-Critic - Yumeka Nagano
• Robust MDPs - Chris Guthrie