Improving reinforcement learning agents using genetic algorithms

Authors:
Akram Beigi;Hamid Parvin;Nasser Mozayani;Behrouz Minaei
Affiliations:
Computer Engineering School, Iran University of Science and Technology, Tehran, Iran;Computer Engineering School, Iran University of Science and Technology, Tehran, Iran;Computer Engineering School, Iran University of Science and Technology, Tehran, Iran;Computer Engineering School, Iran University of Science and Technology, Tehran, Iran
Venue:
AMT'10 Proceedings of the 6th international conference on Active media technology
Year:
2010

Citing 6
Cited 1

Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Multi-task reinforcement learning: a hierarchical Bayesian approach

Proceedings of the 24th international conference on Machine learning
A framework for aggregation of multiple reinforcement learning algorithms

A framework for aggregation of multiple reinforcement learning algorithms
Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations

Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations
Evolutionary Multi-objective Optimization in Uncertain Environments: Issues and Algorithms

Evolutionary Multi-objective Optimization in Uncertain Environments: Issues and Algorithms
Evolutionary optimization in uncertain environments-a survey

IEEE Transactions on Evolutionary Computation

Chaotic exploration generator for evolutionary reinforcement learning agents in nondeterministic environments

ICANNGA'11 Proceedings of the 10th international conference on Adaptive and natural computing algorithms - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper a new Reinforcement Learning algorithm was proposed. Q learning is a useful algorithm for agent learning in nondeterministic environment but it is a time consuming algorithm. The presented work applies an evolutionary algorithm for improving Reinforcement Learning algorithm.