Q-Learning With World Models
This work proposes QWM, a framework that leverages world models to perform test-time search over imagined trajectories on top of Q-learning to select high-value actions during both online rollouts and evaluation, and significantly outperforms strong prior state-of-the-art methods on both sample efficiency and performan...
Perry Dong, Yue-Ru Jia, Chelsea Finn et al.
· 2 citations