Equivariant Action Sampling for Reinforcement Learning and Planning
This work addresses a domain-specific problem for robotic manipulation and continuous control tasks, offering an incremental improvement by incorporating symmetry into existing sampling methods.
The paper tackles the challenge of preserving symmetry in sampling-based planning and control for reinforcement learning, introducing an approach that enforces symmetry and showing it drastically outperforms naive sampling in a coordinate regression problem and multiple continuous control tasks.
Reinforcement learning (RL) algorithms for continuous control tasks require accurate sampling-based action selection. Many tasks, such as robotic manipulation, contain inherent problem symmetries. However, correctly incorporating symmetry into sampling-based approaches remains a challenge. This work addresses the challenge of preserving symmetry in sampling-based planning and control, a key component for enhancing decision-making efficiency in RL. We introduce an action sampling approach that enforces the desired symmetry. We apply our proposed method to a coordinate regression problem and show that the symmetry aware sampling method drastically outperforms the naive sampling approach. We furthermore develop a general framework for sampling-based model-based planning with Model Predictive Path Integral (MPPI). We compare our MPPI approach with standard sampling methods on several continuous control tasks. Empirical demonstrations across multiple continuous control environments validate the effectiveness of our approach, showcasing the importance of symmetry preservation in sampling-based action selection.