Model-Free Representation Learning and Exploration in Low-Rank MDPs

The low-rank MDP has emerged as an important model for studying representation learning and exploration in reinforcement learning. With a known representation, several model-free exploration strategies exist. In contrast, all algorithms for the unknown representation setting are model-based, thereby requiring the ability to model the full dynamics. In this work, we present the first model-free representation learning algorithms for low-rank MDPs. The key algorithmic contribution is a new minimax representation learning objective, for which we provide variants with differing tradeoffs …

algorithms contrast dynamics exploration free low reinforcement reinforcement learning representation representation learning strategies studying work