Michel, Thomas

2 publications

ICLR 2026 Octax: Accelerated CHIP-8 Arcade Environments for Reinforcement Learning in JAX Waris Radji, Thomas Michel, Hector Piteau

TMLR 2023 Regret Bounds for Satisficing in Multi-Armed Bandit Problems Thomas Michel, Hossein Hajiabolhassan, Ronald Ortner