Will it Blend? Composing Value Functions in Reinforcement Learning

Benjamin van Niekerk, Steven James, Adam Earle, Benjamin Rosman
July 2018
PDF Cite Project

Abstract

An important property for lifelong-learning agents is the ability to combine existing skills to solve unseen tasks. In general, however, it is unclear how to compose skills in a principled way. We provide a “recipe” for optimal value function composition in entropy-regularised reinforcement learning (RL) and then extend this to the standard RL setting. Composition is demonstrated in a video game environment, where an agent with an existing library of policies is able to solve new tasks without the need for further learning.

Type
Workshop paper
Publication
The 2nd Lifelong Learning: A Reinforcement Learning Approach (LLARLA) Workshop @ FAIM
Reinforcement Learning Composition Entropy-regularised Reinforcement Learning
Steven James
Steven James
Deputy Lab Director

My research interests include reinforcement learning and planning.

Adam Earle
Adam Earle
Benjamin Rosman
Benjamin Rosman
Lab Director

I am a Professor in the School of Computer Science and Applied Mathematics at the University of the Witwatersrand in Johannesburg. I work in robotics, artificial intelligence, decision theory and machine learning.