Guy Tennenholtz

Spectral Bellman Method: Unifying Representation and Exploration in RL

Descriptive History Representations: Learning Representations by Answering Questions

Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spaces

Benchmarks for Reinforcement Learning with Biased Offline Data and Imperfect Simulators

Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models

Preference Adaptive and Sequential Text-to-Image Generation