3 papers
cs.IR2026
TokenMinds: Pretrained User Tokens and Embeddings for User Understanding in Large Recommender Systems
Qingyun Liu, Bo Yan, Yang Liu +15
User modeling in industrial recommender systems typically produces dense embeddings, which suffer from representational constraints inherent to fixed-dimensional vectors. An emergi…
cs.LG2026
ME-IGM: Individual-Global-Max in Maximum Entropy Multi-Agent Reinforcement Learning
Wen-Tse Chen, Yuxuan Li, Shiyu Huang +2
Multi-agent credit assignment is a fundamental challenge for cooperative multi-agent reinforcement learning (MARL), where a team of agents learn from shared reward signals. The Ind…
cs.LG2026
Continual Policy Distillation from Distributed Reinforcement Learning Teachers
Yuxuan Li, Qijun He, Mingqi Yuan +3
Continual Reinforcement Learning (CRL) aims to develop lifelong learning agents to continuously acquire knowledge across diverse tasks while mitigating catastrophic forgetting. Thi…