Saved in:
Bibliographic Details
Main Authors: Tao, Nigel, Baxter, Jonathan, Weaver, Lex
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.03211
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Network routing is a distributed decision problem which naturally admits numerical performance measures, such as the average time for a packet to travel from source to destination. OLPOMDP, a policy-gradient reinforcement learning algorithm, was successfully applied to simulated network routing under a number of network models. Multiple distributed agents (routers) learned co-operative behavior without explicit inter-agent communication, and they avoided behavior which was individually desirable, but detrimental to the group's overall performance. Furthermore, shaping the reward signal by explicitly penalizing certain patterns of sub-optimal behavior was found to dramatically improve the convergence rate.