2 papers
stat.ME2026
Finite-Sample Theory for Fitted Q-Iteration When Actions Are Functions
Gefei Lin, Rui Miao, Xiaoke Zhang
Offline reinforcement learning seeks optimal decision rules from previously collected data. In some applications, a decision can be an entire function, such as a fluence map in rad…
cs.AI2026
TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing
Yuanpeng Li, Gefei Lin, Annie Qu +1
Soft Actor-Critic (SAC) and its variants dominate Multi-Task Reinforcement Learning (MTRL) due to their off-policy sample efficiency, while on-policy methods such as Proximal Polic…