Hierarchical Adaptive Value Estimation for Multi-modal Visual Reinforcement Learning

Integrating RGB frames with alternative modality inputs is gaining increasing traction in many vision-based reinforcement learning (RL) applications. Existing multi-modal vision-based RL methods usually follow a Global Value Estimation (GVE) pipeline, which uses a fused modality feature to obtain a unified global environmental description. However, such a feature-level fusion paradigm with a single critic may fall short in policy learning as it tends to overlook the distinct values of each modality. To remedy this, this paper proposes a Local modalitycustomized Value Estimation (LVE) paradigm, which dynamically estimates the contribution and adjusts the importance weight of each modality from a valuelevel perspective. Furthermore, a task-contextual re-fusion process is developed to achieve a task-level re-balance of estimations from both feature and value levels. To this end, a Hierarchical Adaptive Value Estimation (HAVE) framework is formed, which adaptively coordinates the contributions of individual modalities as well as their collective efficacy. Agents trained by HAVE are able to exploit the unique characteristics of various modalities while capturing their intricate interactions, achieving substantially improved performance. We specifically highlight the potency of our approach within the challenging landscape of autonomous driving, utilizing the CARLA benchmark with neuromorphic event and depth data to demonstrate HAVE's capability and the effectiveness of its distinct components. The code of our paper can be found at https://github.com/Yara-HYR/HAVE . RGB Critic 𝑞 𝑀 1 (d) Local modality-customized Value Estimation (LVE) 𝑞 𝑡 𝑙 𝑞 𝑀 2 𝑤 𝑀 1 𝑤 𝑀 2 𝑟 𝑡 𝑞 𝑡 𝑔 Critic (c) Global Value Estimation (GVE)