Asynchronous execution yields 2.9x-16.9x speedups across Jacobi, value iteration, and SCF methods; Anderson acceleration succeeds only under evaluation-level perturbation, not iterate-level corruption.
Anderson Acceleration for Reinforcement Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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.
fields
cs.DC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Fault Tolerance of Accelerated Asynchronous Fixed-Point Iterations on Flexible Computing Infrastructure
Asynchronous execution yields 2.9x-16.9x speedups across Jacobi, value iteration, and SCF methods; Anderson acceleration succeeds only under evaluation-level perturbation, not iterate-level corruption.