Learning Fused State Representations for Control from Multi-View Observations
This addresses a challenge in multi-view reinforcement learning for agents needing robust perception, but it appears incremental as it builds on existing representation learning methods.
The paper tackles the problem of learning compact and task-relevant state representations from multi-view observations in reinforcement learning, particularly in the presence of redundancy, distracting information, or missing views, and demonstrates that their method outperforms existing approaches and maintains high performance in realistic scenarios.
Multi-View Reinforcement Learning (MVRL) seeks to provide agents with multi-view observations, enabling them to perceive environment with greater effectiveness and precision. Recent advancements in MVRL focus on extracting latent representations from multiview observations and leveraging them in control tasks. However, it is not straightforward to learn compact and task-relevant representations, particularly in the presence of redundancy, distracting information, or missing views. In this paper, we propose Multi-view Fusion State for Control (MFSC), firstly incorporating bisimulation metric learning into MVRL to learn task-relevant representations. Furthermore, we propose a multiview-based mask and latent reconstruction auxiliary task that exploits shared information across views and improves MFSC's robustness in missing views by introducing a mask token. Extensive experimental results demonstrate that our method outperforms existing approaches in MVRL tasks. Even in more realistic scenarios with interference or missing views, MFSC consistently maintains high performance.