5 papers
Language Model Distillation: A Temporal Difference Imitation Learning Perspective
Zishun Yu, Shangzhe Li, Xinhua Zhang
Large language models have led to significant progress across many NLP tasks, although their massive sizes often incur substantial computational costs. Distillation has become a co…
Towards Efficient Collaboration via Graph Modeling in Reinforcement Learning
Wenzhe Fan, Zishun Yu, Chengdong Ma +3
In multi-agent reinforcement learning, a commonly considered paradigm is centralized training with decentralized execution. However, in this framework, decentralized execution rest…
-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis
Zishun Yu, Yunzhe Tao, Liyu Chen +2
Program synthesis aims to create accurate, executable programs from problem specifications, specifically from natural language descriptions in our context. Recent studies have leve…
Slowly Changing Adversarial Bandit Algorithms are Efficient for Discounted MDPs
Ian A. Kash, Lev Reyzin, Zishun Yu
Reinforcement learning generalizes multi-armed bandit problems with additional difficulties of a longer planning horizon and unknown transition kernel. We explore a black-box reduc…
Orthogonal Gromov-Wasserstein Discrepancy with Efficient Lower Bound
Hongwei Jin, Zishun Yu, Xinhua Zhang
Comparing structured data from possibly different metric-measure spaces is a fundamental task in machine learning, with applications in, e.g., graph classification. The Gromov-Wass…