Pre-trained Word Embeddings for Goal-conditional Transfer Learning in Reinforcement Learning
arXiv:2007.05196
Abstract
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.
arXiv commentPaper accepted to the ICML 2020 Language in Reinforcement Learning (LaReL) Workshop
References in corpus (6)
- How transferable are features in deep neural networks?
- Agent57: Outperforming the Atari Human Benchmark
- Grounded Language Learning in a Simulated 3D World
- Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences
- Diversity is All You Need: Learning Skills without a Reward Function
- Learning to Understand Goal Specifications by Modelling Reward