Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs
Luke J. Huang, Zhuoyang Zhang, Qinghao Hu +2
Asynchronous reinforcement learning has become increasingly central to scaling LLM post-training, delivering major throughput gains by decoupling rollout generation from policy upd…
cs.LG2021
Escaping from Zero Gradient: Revisiting Action-Constrained Reinforcement Learning via Frank-Wolfe Policy Optimization
Jyun-Li Lin, Wei Hung, Shang-Hsuan Yang +2
Action-constrained reinforcement learning (RL) is a widely-used approach in various real-world applications, such as scheduling in networked systems with resource constraints and c…