paint-brush
How Approximate Anchored Value Iteration Handles Errors in Decision-Making Modelsby@anchoring

How Approximate Anchored Value Iteration Handles Errors in Decision-Making Models

by AnchoringJanuary 14th, 2025
Read on Terminal Reader
Read this story w/o Javascript
tldt arrow

Too Long; Didn't Read

Approximate Anchored Value Iteration (Apx-Anc-VI) is shown to be robust against Bellman operator evaluation errors, offering performance comparable to standard Approximate VI.
featured image - How Approximate Anchored Value Iteration Handles Errors in Decision-Making Models
Anchoring HackerNoon profile picture
0-item

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.

Abstract and 1 Introduction

1.1 Notations and preliminaries

1.2 Prior works

2 Anchored Value Iteration

2.1 Accelerated rate for Bellman consistency operator

2.2 Accelerated rate for Bellman optimality opera

3 Convergence when y=1

4 Complexity lower bound

5 Approximate Anchored Value Iteration

6 Gauss–Seidel Anchored Value Iteration

7 Conclusion, Acknowledgments and Disclosure of Funding and References

A Preliminaries

B Omitted proofs in Section 2

C Omitted proofs in Section 3

D Omitted proofs in Section 4

E Omitted proofs in Section 5

F Omitted proofs in Section 6

G Broader Impacts

H Limitations

5 Approximate Anchored Value Iteration

In this section, we show that the anchoring mechanism is robust against evaluation errors of the Bellman operator, just as much as the standard approximate VI.




This paper is available on arxiv under CC BY 4.0 DEED license.