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.

该研究通过对比 2D 与 3D 表现，研究了 3D 神经网络在可视化强化学习任务中的效能，特别关注了基于 3D 点云的设计选择，研究表明在涉及到 agent-object/object-object 关系编码时，3D 点云比 2D 图像更有效，尤其在复杂的机器人操作任务中。