3 papers
cs.LG2026
COPC: Coupled Off-Policy Correction for Asynchronous LLM Reinforcement Learning
Zicheng Hu, Zhijian Zhou, Xuan Zhang +7
Asynchronous RL accelerates large language model post-training by decoupling rollout generation from optimization, but trains on stale trajectories. Existing methods primarily corr…
math.OC2022
Uniform boundedness for the optimal controls of a discontinuous, non-convex Bolza problem
Piernicola Bettiol, Carlo Mariconda
We consider a Bolza type optimal control problem of the form \begin{equation}\min J_{t}(y,u):=\int_t^TΛ(s,y(s), u(s))\,ds+g(y(T))\tag{P}\end{equation} Subject to: \begin{eq…
math.OC2019
Necessary Optimality Conditions For Average Cost Minimization Problems
Piernicola Bettiol, Nathalie Khalil
Control systems involving unknown parameters appear a natural framework for applications in which the model design has to take into account various uncertainties. In these circumst…