< Back to previous page
Pre-trained word embeddings for goal-conditional transfer learning in reinforcement learning
Book Contribution - Book Abstract Conference Contribution
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.
Book: Language in Reinforcement Learning Workshop at ICML 2020, the 37th International Conference on Machine Learning, 18 July, 2020, Vienna Austria
Pages: 1 - 6