Explore a 13-minute conference presentation from SIGIR 2024 that delves into enhancing long-term recommender system performance through user-oriented exploration policies. Learn how authors Changshuo Zhang, Sirui Chen, Xiao Zhang, Sunhao Dai, Weijie Yu and Jun Xu address the challenges of session-based recommendations and long-term user engagement. Discover innovative approaches to reinforcement learning in recommendation systems, focusing on exploration strategies that adapt to user preferences over time. Gain insights into methods for balancing immediate user satisfaction with sustained system performance in the context of session-based recommendation scenarios.