Skip to yearly menu bar Skip to main content


Poster

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

Ofir Marom · Benjamin Rosman

Room 517 AB #151

Keywords: [ Multitask and Transfer Learning ] [ Model-Based RL ]


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.

Live content is unavailable. Log in and register to view live content