<ul><li>In data-driven decision-making, knowledge transfer can help address data scarcity in new ventures.</li><li>The authors propose a framework of Transferred Fitted $Q$-Iteration algorithm for knowledge transfer.</li><li>The framework enables direct estimation of the optimal action-state function using both target and source data.</li><li>The approach shows improved learning error rates compared to single task learning, both theoretically and empirically.</li></ul>

Data-Driven Knowledge Transfer in Batch $Q^*$ Learning

Discover more