5 papers
Reconciling Contradictory Views on the Effectiveness of SFT in LLMs: An Interaction Perspective
Junpeng Zhang, Lei Cheng, Guoxi Zhang +3
This paper explores a scientific question in supervised fine-tuning (SFT): why SFT is broadly effective for small-scale deep neural networks, yet can produce inconsistent or even d…
SPHERE: Mitigating the Loss of Spectral Plasticity in Mixture-of-Experts for Deep Reinforcement Learning
Lirui Luo, Guoxi Zhang, Hongming Xu +2
In deep reinforcement learning (DRL), an agent is trained from a stream of experience. In a continual learning setting, such agents can suffer from plasticity loss: their ability t…
On Modeling Long-Term User Engagement from Stochastic Feedback
Guoxi Zhang, Xing Yao, Xuanji Xiao
An ultimate goal of recommender systems (RS) is to improve user engagement. Reinforcement learning (RL) is a promising paradigm for this goal, as it directly optimizes overall perf…
Behavior Estimation from Multi-Source Data for Offline Reinforcement Learning
Guoxi Zhang, Hisashi Kashima
Offline reinforcement learning (RL) have received rising interest due to its appealing data efficiency. The present study addresses behavior estimation, a task that lays the founda…
Batch Reinforcement Learning from Crowds
Guoxi Zhang, Hisashi Kashima
A shortcoming of batch reinforcement learning is its requirement for rewards in data, thus not applicable to tasks without reward functions. Existing settings for lack of reward, s…