2022
Dropout Q-Functions for Doubly Efficient Reinforcement Learning
ICLR 2022poster
Randomized ensembled double Q-learning (REDQ) (Chen et al., 2021b) has recently achieved state-of-the-art sample efficiency on continuous-action reinforcement learning benchmarks. This superior sample efficiency is made possible by using a large Q-function ensemble. However, REDQ is much less comput…