Multi-Agent Reinforcement Learning and Genetic Policy Sharing

Details Multi-Agent Reinforcement Learning and Genetic Policy Sharing Multi-Agent Reinforcement Learning and Genetic Policy Sharing

2008-12-09

arxiv.org/abs/0812.1599v1

Computer Science

Multiagent Systems

7 pages, 11 figures

Scientific paper

The effects of policy sharing between agents in a multi-agent dynamical system has not been studied extensively. I simulate a system of agents optimizing the same task using reinforcement learning, to study the effects of different population densities and policy sharing. I demonstrate that sharing policies decreases the time to reach asymptotic behavior, and results in improved asymptotic behavior.

Affiliated with

Also associated with

No associations

Rating

Multi-Agent Reinforcement Learning and Genetic Policy Sharing does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Multi-Agent Reinforcement Learning and Genetic Policy Sharing, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Multi-Agent Reinforcement Learning and Genetic Policy Sharing will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-281636