Learning latent state representation for speeding up exploration
This work addresses exploration bottlenecks for reinforcement learning agents in complex environments, though it appears incremental as it builds on existing representation learning and entropy-based methods.
The paper tackles the challenge of exploration in reinforcement learning with high-dimensional spaces and sparse rewards by learning latent state representations from prior experience, which reduces the search space dimensionality and improves exploration efficiency in a simulated object pushing environment.
Exploration is an extremely challenging problem in reinforcement learning, especially in high dimensional state and action spaces and when only sparse rewards are available. Effective representations can indicate which components of the state are task relevant and thus reduce the dimensionality of the space to explore. In this work, we take a representation learning viewpoint on exploration, utilizing prior experience to learn effective latent representations, which can subsequently indicate which regions to explore. Prior experience on separate but related tasks help learn representations of the state which are effective at predicting instantaneous rewards. These learned representations can then be used with an entropy-based exploration method to effectively perform exploration in high dimensional spaces by effectively lowering the dimensionality of the search space. We show the benefits of this representation for meta-exploration in a simulated object pushing environment.