Regularized Anderson Acceleration for Off-Policy Deep Reinforcement Learning

Wenjie Shi, Shiji Song, Hui Wu, Ya-Chu Hsu, Cheng Wu, Gao Huang

Feb-13-2026, 20:02:50 GMT–Neural Information Processing Systems 

Model-free deepreinforcement learning (RL)algorithms havebeenwidely used for a range of complex control tasks.