On the Efficacy of 3D Point Cloud Reinforcement Learning
This work addresses the need for systematic evaluation of 3D representations in visual RL for robotic manipulation and control tasks, though it is incremental as it builds on existing 3D representation research.
The paper tackled the problem of comparing 3D point cloud reinforcement learning with 2D methods, finding that 3D point cloud RL significantly outperforms 2D methods when agent-object or object-object relationship encoding is crucial.
Recent studies on visual reinforcement learning (visual RL) have explored the use of 3D visual representations. However, none of these work has systematically compared the efficacy of 3D representations with 2D representations across different tasks, nor have they analyzed 3D representations from the perspective of agent-object / object-object relationship reasoning. In this work, we seek answers to the question of when and how do 3D neural networks that learn features in the 3D-native space provide a beneficial inductive bias for visual RL. We specifically focus on 3D point clouds, one of the most common forms of 3D representations. We systematically investigate design choices for 3D point cloud RL, leading to the development of a robust algorithm for various robotic manipulation and control tasks. Furthermore, through comparisons between 2D image vs 3D point cloud RL methods on both minimalist synthetic tasks and complex robotic manipulation tasks, we find that 3D point cloud RL can significantly outperform the 2D counterpart when agent-object / object-object relationship encoding is a key factor.