A Multi-Agent, Policy-Gradient approach to Network Routing

Abstract

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.

Cited by in corpus (7)

• Optimal and Approximate Q-value Functions for Decentralized POMDPs
• Experiments with Infinite-Horizon, Policy-Gradient Estimation
• Modelling the Dynamic Joint Policy of Teammates with Attention Multi-agent DDPG
• A Bayesian Framework for Digital Twin-Based Control, Monitoring, and Data Collection in Wireless Systems
• Decentralized Delay Optimal Control for Interference Networks with Limited Renewable Energy Storage
• Q-adaptive: A Multi-Agent Reinforcement Learning Based Routing on Dragonfly Network
• MAMRL: Exploiting Multi-agent Meta Reinforcement Learning in WAN Traffic Engineering