Aggressive Q-Learning with Ensembles: Achieving Both High Sample Efficiency and High Asymptotic Performance. (arXiv:2111.09159v2 [cs.LG] UPDATED)

Recent advances in model-free deep reinforcement learning (DRL) show that
simple model-free methods can be highly effective in challenging
high-dimensional continuous control tasks. In particular, Truncated Quantile
Critics (TQC) achieves state-of-the-art asymptotic training performance on the
MuJoCo benchmark with a distributional representation of critics; and
Randomized Ensemble Double Q-Learning (REDQ) achieves high sample efficiency
that is competitive with state-of-the-art model-based methods using a high
update-to-data ratio and target randomization. In this paper, we propose a
novel model-free algorithm, Aggressive Q-Learning …

arxiv efficiency performance q-learning