• Publication Position: Leverage Foundational Models for Black-Box Optimization
• Publication Understanding Learning from Human Preferences
• Publication MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking
• Publication Diffusion model predictive control
• Publication Online RL in Linearly $q^\pi$-Realizable MDPs Is as Easy as in Linear MDPs If You Learn What to Ignore
• Publication Distributional Bellman Operators over Mean-embeddings
• Publication Exposing Limitations of Language Model Agents in Sequential-Task Compositions on the Web
• Publication Self-Predictive Universal AI
• Publication Robust Exploration via Clustering-based Density Estimation
• Publication An Introduction to Universal Artificial Intelligence