TL;DR —
Gauss-Seidel Anchored Value Iteration (GS-Anc-VI) combines anchoring with Gauss-Seidel updates to improve convergence rates for finite state-action spaces, offering fast convergence for Bellman optimality and consistency operators.
Authors:
(1) Jongmin Lee, Department of Mathematical Science, Seoul National University;
(2) Ernest K. Ryu, Department of Mathematical Science, Seoul National University and Interdisciplinary Program in Artificial Intelligence, Seoul National University.
1.1 Notations and preliminaries
2.1 Accelerated rate for Bellman consistency operator
2.2 Accelerated rate for Bellman optimality opera
5 Approximate Anchored Value Iteration
6 Gauss–Seidel Anchored Value Iteration
7 Conclusion, Acknowledgments and Disclosure of Funding and References
6 Gauss–Seidel Anchored Value Iteration

This paper is available on arxiv under CC BY 4.0 DEED license.
[story continues]
Written by
@anchoring
Anchoring provides a steady start, grounding decisions and perspectives in clarity and confidence.
Topics and
tags
tags
reinforcement-learning|dynamic-programming|nesterov-acceleration|machine-learning-optimization|value-iteration|value-iteration-convergence|bellman-error|gauss-seidel-anchored-vi
This story on HackerNoon has a decentralized backup on Sia.
Transaction ID: ifr75z1D0QlS8_bNNNP3J46HnV7gi1vy68ZF2ydKxd0
