Distributed Reinforcement Learning in Multi-Agent Networked Systems

Cited by: 0|Views18

Abstract:

We study distributed reinforcement learning (RL) for a network of agents. The objective is to find localized policies that maximize the (discounted) global reward. In general, scalability is a challenge in this setting because the size of the global state/action space can be exponential in the number of agents. Scalable algorithms are o...More

Code:

Data:

Get fulltext within 24h
Bibtex
Your rating :
0

 

Tags
Comments