Predictive Coding for Boosting Deep Reinforcement Learning with Sparse Rewards

Xingyu Lu, Pieter Abbeel, Stas Tiomkin

TL;DR: We apply predictive coding to provide reward signals in sparse reward problems.

Abstract: While recent progress in deep reinforcement learning has enabled robots to learn complex behaviors, tasks with long horizons and sparse rewards remain an ongoing challenge. In this work, we propose an effective reward shaping method through predictive coding to tackle sparse reward problems. By learning predictive representations offline and using these representations for reward shaping, we gain access to reward signals that understand the structure and dynamics of the environment. In particular, our method achieves better learning by providing reward signals that 1) understand environment dynamics 2) emphasize on features most useful for learning 3) resist noise in learned representations through reward accumulation. We demonstrate the usefulness of this approach in different domains ranging from robotic manipulation to navigation, and we show that reward signals produced through predictive coding are as effective for learning as hand-crafted rewards.

Keywords: reinforcement learning, representation learning, reward shaping, predictive coding