Multi-goal Q-learning of cooperative teams

Authors:
Jing Li;Zhaohan Sheng;KwanChew Ng
Affiliations:
School of Engineering, Nanjing Agricultural University, Nanjing, China;School of Management Science and Engineering, Nanjing University, Nanjing, China;School of Management Science and Engineering, Nanjing University, Nanjing, China
Venue:
Expert Systems with Applications: An International Journal
Year:
2011

Citing 10
Cited 2

Technical Note: \cal Q-Learning

Machine Learning
Target Reaching by Using Visual Information and Q-learning Controllers

Autonomous Robots
Learning behavior-selection by emotions and cognition in a multi-goal robot task

The Journal of Machine Learning Research
Learning Rates for Q-learning

The Journal of Machine Learning Research
An Evolutionary Dynamical Analysis of Multi-Agent Learning in Iterated Games

Autonomous Agents and Multi-Agent Systems
A two-layered multi-agent reinforcement learning model and algorithm

Journal of Network and Computer Applications
Shaping multi-agent systems with gradient reinforcement learning

Autonomous Agents and Multi-Agent Systems
Optimistic-Pessimistic Q-Learning Algorithm for Multi-Agent Systems

MATES '08 Proceedings of the 6th German conference on Multiagent System Technologies
A reinforcement learning model for supply chain ordering management: An application to the beer game

Decision Support Systems
Dynamic packaging in e-retailing with stochastic demand over finite horizons: A Q-learning approach

Expert Systems with Applications: An International Journal

A novel modular Q-learning architecture to improve performance under incomplete learning in a grid soccer game

Engineering Applications of Artificial Intelligence
Adaptive learning algorithm of self-organizing teams

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	12.05

Visualization

Abstract

This paper studies a multi-goal Q-learning algorithm of cooperative teams. Member of the cooperative teams is simulated by an agent. In the virtual cooperative team, agents adapt its knowledge according to cooperative principles. The multi-goal Q-learning algorithm is approached to the multiple learning goals. In the virtual team, agents learn what knowledge to adopt and how much to learn (choosing learning radius). The learning radius is interpreted in Section 3.1. Five basic experiments are manipulated proving the validity of the multi-goal Q-learning algorithm. It is found that the learning algorithm causes agents to converge to optimal actions, based on agents' continually updated cognitive maps of how actions influence learning goals. It is also proved that the learning algorithm is beneficial to the multiple goals. Furthermore, the paper analyzes how sensitive the learning performance is affected by the parameter values of the learning algorithm.