mlsanityData to 7 Oct 2026

Anderson Acceleration for Reinforcement Learning

arXiv 1809.09501 ↗First posted 25 Sep 2018cs.LG stat.MLcited by 14

Not on the map. Why?

Abstract (arXiv)

Anderson acceleration is an old and simple method for accelerating the computation of a fixed point. However, as far as we know and quite surprisingly, it has never been applied to dynamic programming or reinforcement learning. In this paper, we explain briefly what Anderson acceleration is and how it can be applied to value iteration, this being supported by preliminary experiments showing a significant speed up of convergence, that we critically discuss. We also discuss how this idea could be applied more generally to (deep) reinforcement learning.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 1; 2023: 6; 2024: 2; 2025: 2; 2026: 1.

14 papers.

Sort:

  1. 2023Accelerating Value Iteration with Anchoringcited by 10
  2. 2021Damped Anderson Mixing for Deep Reinforcement Learning: Acceleration, Convergence, and Stabilizationcited by 7
  3. 2021Stochastic Anderson Mixing for Nonconvex Stochastic Optimizationcited by 6
  4. 2024Deflated Dynamics Value Iterationcited by 4
  5. 2023Anderson Acceleration For Bioinformatics-Based Machine Learningcited by 2
  6. 2023Enhancing Electrical Impedance Tomography reconstruction using Learned Half-Quadratic Splitting Networks with Anderson Accelerationcited by 2
  7. 2023From Optimization to Control: Quasi Policy Iterationcited by 2
  8. 2025Rank-One Modified Value Iterationcited by 2
  9. 2024PID Accelerated Temporal Difference Algorithmscited by 1
  10. 2022An Efficient Nonlinear Acceleration method that Exploits Symmetry of the Hessiancited by 0
  11. 2023Acceleration in Policy Optimizationcited by 0
  12. 2023Improved Convergence Factor of Windowed Anderson Acceleration for Symmetric Fixed-Point Iterationscited by 0
2 more
  1. 2025FedOSAA: Improving Federated Learning with One-Step Anderson Accelerationcited by 0
  2. 2026Heavy-Ball Q-Learning with Residual Weighting Correctioncited by 0