• Publication Learning Interactive Real-World Simulator
• Publication Equivariant MuZero
• Publication RLHF and IIA: Perverse Incentives
• Publication Directly Fine-Tuning Diffusion Models on Differentiable Rewards
• Publication Near-Minimax-Optimal Distributional RL with a Generative Model
• Publication AlphaTensor for Optimizing Quantum Computations
• Publication A density estimation perspective on learning from pairwise human preferences
• Publication Meta-in-context learning in large language models
• Publication A Distributional Analogue to the Successor Representation
• Publication Replay Across Experiments