Global Policy Construction in Modular Reinforcement Learning

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

Authors

• Ruohan Zhang
• Zhao Song Adobe Research
• Dana Ballard

Keywords

No keywords are indexed for this paper.