AI RESEARCH

Provable Multi-Task Reinforcement Learning: A Representation Learning Framework with Low Rank Rewards

arXiv CS.LG

ArXi:2604.03891v1 Announce Type: new Multi-task representation learning (MTRL) is an approach that learns shared latent representations across related tasks, facilitating collaborative learning that improves the overall learning efficiency. This paper studies MTRL for multi-task reinforcement learning (RL), where multiple tasks have the same state-action space and transition probabilities, but different rewards. We consider T linear Marko Decision Processes (MDPs) where the reward functions and transition dynamics admit linear feature embeddings of dimension d.