Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning

Ofir Marom, Benjamin Rosman
December 2018
PDF Cite Supplementary Material

Abstract

Object-oriented representations in reinforcement learning have shown promise in transfer learning, with previous research introducing a propositional object-oriented framework that has provably efficient learning bounds with respect to sample complexity. However, this framework has limitations in terms of the classes of tasks it can efficiently learn. In this paper we introduce a novel deictic object-oriented framework that has provably efficient learning bounds and can solve a broader range of tasks. Additionally, we show that this framework is capable of zero-shot transfer of transition dynamics across tasks and demonstrate this empirically for the Taxi and Sokoban domains.

Type
Conference paper
Publication
Advances in Neural Information Processing Systems
Reinforcement Learning Transfer Learning Object-oriented Reinforcement Learning
Ofir Marom
Ofir Marom
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.