Work

Multi-Agent Reinforcement Learning and Genetic Policy Sharing

Year: 2008

Type: preprint

Abstract: 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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.0812.1599

Author: Ellowitz, Jake

Language: English

Topic: Reinforcement Learning in Robotics

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W1670191348

Cites: 1

Cited by:

Related to: 10