A Model-Free Universal AI

The paper introduces Universal AI with Q-Induction (AIQI), the first model-free agent that is proven to be asymptotically ε-optimal in general reinforcement learning. AIQI utilizes universal induction over distributional action-value functions rather than traditional policies or environment models, enhancing the landscape of universal agents. This advancement is significant for practitioners as it offers a new approach to designing agents that do not rely on explicit environmental models, potentially simplifying the development of robust RL systems.