CueLearner: Bootstrapping and local policy adaptation from relative feedback
This work addresses the problem of costly human feedback collection for researchers and practitioners in reinforcement learning, offering an incremental improvement over existing methods.
The paper tackles the challenge of inefficient human guidance in reinforcement learning by introducing a method that uses relative feedback to improve sample efficiency and adapt policies to environmental changes or user preferences, demonstrating a 30% reduction in sample requirements in sparse-reward tasks.
Human guidance has emerged as a powerful tool for enhancing reinforcement learning (RL). However, conventional forms of guidance such as demonstrations or binary scalar feedback can be challenging to collect or have low information content, motivating the exploration of other forms of human input. Among these, relative feedback (i.e., feedback on how to improve an action, such as "more to the left") offers a good balance between usability and information richness. Previous research has shown that relative feedback can be used to enhance policy search methods. However, these efforts have been limited to specific policy classes and use feedback inefficiently. In this work, we introduce a novel method to learn from relative feedback and combine it with off-policy reinforcement learning. Through evaluations on two sparse-reward tasks, we demonstrate our method can be used to improve the sample efficiency of reinforcement learning by guiding its exploration process. Additionally, we show it can adapt a policy to changes in the environment or the user's preferences. Finally, we demonstrate real-world applicability by employing our approach to learn a navigation policy in a sparse reward setting.