Reinforcement learning (RL) algorithms typically start tabula rasa, without any prior knowledge of the environment, and without any prior skills. This however often leads to low sample efficiency, requiring a large amount of interaction with the environment. This is especially true in a lifelong learning setting, in which the agent needs to continually extend its capabilities. In this paper, we examine how a pre-trained task-independent language model can make a goal-conditional RL agent more sample efficient. We do this by facilitating transfer learning between different related tasks. We experimentally demonstrate our approach on a set of object navigation tasks.
@article{arxiv.2007.05196,
title = {Pre-trained Word Embeddings for Goal-conditional Transfer Learning in Reinforcement Learning},
author = {Matthias Hutsebaut-Buysse and Kevin Mets and Steven Latré},
journal= {arXiv preprint arXiv:2007.05196},
year = {2020}
}
Comments
Paper accepted to the ICML 2020 Language in Reinforcement Learning (LaReL) Workshop