English

Randomized Ensembled Double Q-Learning: Learning Fast Without a Model

Machine Learning 2021-03-19 v2 Artificial Intelligence

Abstract

Using a high Update-To-Data (UTD) ratio, model-based methods have recently achieved much higher sample efficiency than previous model-free methods for continuous-action DRL benchmarks. In this paper, we introduce a simple model-free algorithm, Randomized Ensembled Double Q-Learning (REDQ), and show that its performance is just as good as, if not better than, a state-of-the-art model-based algorithm for the MuJoCo benchmark. Moreover, REDQ can achieve this performance using fewer parameters than the model-based method, and with less wall-clock run time. REDQ has three carefully integrated ingredients which allow it to achieve its high performance: (i) a UTD ratio >> 1; (ii) an ensemble of Q functions; (iii) in-target minimization across a random subset of Q functions from the ensemble. Through carefully designed experiments, we provide a detailed analysis of REDQ and related model-free algorithms. To our knowledge, REDQ is the first successful model-free DRL algorithm for continuous-action spaces using a UTD ratio >> 1.

Cite

@article{arxiv.2101.05982,
  title  = {Randomized Ensembled Double Q-Learning: Learning Fast Without a Model},
  author = {Xinyue Chen and Che Wang and Zijian Zhou and Keith Ross},
  journal= {arXiv preprint arXiv:2101.05982},
  year   = {2021}
}

Comments

Published as a conference paper at ICLR 2021

R2 v1 2026-06-23T22:11:35.848Z