Adaptive co-evolution using reinforcement learning

Added Title

Humanoid, Nanotechnology, Information Technology, Communication and Control Environment Management International Conference (3rd : 2007 : Century Park Hotel, Manila, Philippines)

Authors

Remedios de Dios Bulos, De La Salle University, Manila
Rex Benedict Amurao, De La Salle University, Manila
Allan David Gallardo, De La Salle University, Manila
Marvin Royce Moreno, De La Salle University, Manila

College

Gokongwei College of Engineering

Document Type

Conference Proceeding

Source Title

Third Humanoid, Nanotechnology, Information Technology, Communication and Control Environment Management (HNICEM) International Conference

Publication Date

3-15-2007

Abstract

The field of co-evolution is focused on evolving agents based on the fitness of another evolving agent; in this way, agents are expected to learn from each other. This research aims to develop agents, which would adapt to the skill level of an individual human. Particularly, this study investigates and discusses the behavior of reinforcement learning (RL) as an algorithm for co-evolution. A modified snake game was used to test and evaluate co-evolutionary behavior exhibited by the RL algorithm against genetic algorithm and best response learning algorithm

html

Recommended Citation

Bulos, R. d., Amurao, R. B., Gallardo, A. D., & Moreno, M. R. (2007). Adaptive co-evolution using reinforcement learning. Third Humanoid, Nanotechnology, Information Technology, Communication and Control Environment Management (HNICEM) International Conference Retrieved from https://animorepository.dlsu.edu.ph/faculty_research/3229

Disciplines

Other Engineering | Robotics

Upload File

wf_yes