Retentive Decision Transformer with Adaptive Masking for Reinforcement Learning based Recommendation Systems

arXiv:2403.17634v1 Announce Type: cross
Abstract: Reinforcement Learning-based Recommender Systems (RLRS) have shown promise across a spectrum of applications, from e-commerce platforms to streaming services. Yet, they grapple with challenges, notably in crafting reward functions and harnessing large pre-existing datasets within the RL framework. Recent advancements in offline RLRS provide a solution for how to address these two challenges. However, existing methods mainly rely on the transformer architecture, which, as sequence lengths increase, can introduce challenges associated with computational resources and …

abstract applications arxiv challenges commerce cs.ir cs.lg datasets decision e-commerce e-commerce platforms framework functions masking offline platforms recommendation recommendation systems recommender systems reinforcement reinforcement learning services spectrum streaming streaming services systems transformer type