AAAI Publications, Twenty-Ninth AAAI Conference on Artificial Intelligence

Font Size: 
Global Policy Construction in Modular Reinforcement Learning
Ruohan Zhang, Zhao Song, Dana H. Ballard

Last modified: 2015-03-04

Abstract


We propose a modular reinforcement learning algorithm which decomposes a Markov decision process into independent modules. Each module is trained using Sarsa(lambda). We introduce three algorithms for forming global policy from modules policies, and demonstrate our results using a 2D grid world.

Keywords


Modular reinforcemenet learning

Full Text: PDF