<ul><li>This paper focuses on transfer learning for dynamic decision scenarios modeled by non-stationary finite-horizon Markov decision processes.</li><li>The authors propose a novel re-weighted targeting procedure to construct transferable RL samples and introduce transfer deep Q*-learning.</li><li>The method utilizes neural network approximation with theoretical guarantees and can handle transferable and non-transferable reward functions and transition densities.</li><li>Empirical experiments on synthetic and real datasets demonstrate the effectiveness of the proposed method in non-stationary reinforcement learning contexts.</li></ul>

Deep Transfer $Q$-Learning for Offline Non-Stationary Reinforcement Learning

Discover more