activity
20182026
most citedLogarithmic regret for episodic continuous-time linear-quadratic reinforcement learning over a finite-time horizon

12 citations · 34 across the 14 of their papers we have counts for

collaborators
Showing 2026Show all

2 papers · 1 filter

math.OC2026

Decentralized Decision-Making among Heterogeneous Autonomous Vehicles: An -Potential Game Framework

Anran Hu, Zhexin Wang, Yufei Zhang +1

We study noncooperative multi-vehicle games among heterogeneous autonomous vehicles, where each vehicle adopts a decentralized closed-loop policy based on its own state, and optimi…

math.OC2026

Dynamic Portfolio Optimization under CVaR Constraints

Anran Hu, Silvana M. Pesenti, Xiaofei Shi

We study continuous-time dynamic portfolio optimization under a Conditional Value-at-Risk (CVaR) constraint on the investor's terminal loss. For a general class of convex trading o…