Seeking Visual Discomfort: Curiosity-driven Representations for Reinforcement Learning

TL;DR

This paper introduces a method to enhance exploration in vision-based reinforcement learning by improving sample diversity for state representation learning, leading to better sample efficiency and stability across various environments.

Contribution

It proposes a novel approach that boosts exploration and sample diversity in SRL, significantly improving performance and stability in vision-based RL tasks.

Findings

Boosts visitation of problematic states

Improves learned state representation quality

Outperforms baseline methods in all tested environments

Abstract

Vision-based reinforcement learning (RL) is a promising approach to solve control tasks involving images as the main observation. State-of-the-art RL algorithms still struggle in terms of sample efficiency, especially when using image observations. This has led to increased attention on integrating state representation learning (SRL) techniques into the RL pipeline. Work in this field demonstrates a substantial improvement in sample efficiency among other benefits. However, to take full advantage of this paradigm, the quality of samples used for training plays a crucial role. More importantly, the diversity of these samples could affect the sample efficiency of vision-based RL, but also its generalization capability. In this work, we present an approach to improve sample diversity for state representation learning. Our method enhances the exploration capability of RL algorithms, by taking advantage of the SRL setup. Our experiments show that our proposed approach boosts the visitation of problematic states, improves the learned state representation, and outperforms the baselines for all tested environments. These results are most apparent for environments where the baseline methods struggle. Even in simple environments, our method stabilizes the training, reduces the reward variance, and promotes sample efficiency.