Visual control policies can encounter significant performance degradation
when visual conditions like lighting or camera position differ from those seen
during training -- often exhibiting sharp declines in capability even for minor
differences. In this work, we examine robustness to a suite of these types of
visual changes for RGB-D and point cloud based visual control policies. To
perform these experiments on both model-free and model-based reinforcement
learners, we introduce a novel Point Cloud World Model (PCWM) and point cloud
based control policies. Our experiments show that policies that explicitly
encode point clouds are significantly more robust than their RGB-D
counterparts. Further, we find our proposed PCWM significantly outperforms
prior works in terms of sample efficiency during training. Taken together,
these results suggest reasoning about the 3D scene through point clouds can
improve performance, reduce learning time, and increase robustness for robotic
learners. Project Webpage: this https URL

通过对 RGB-D 和基于点云的视觉控制策略进行实验，我们发现明确编码点云的策略在可视条件变化下显著更加稳健，同时我们提出的点云世界模型（PCWM）在训练过程中大幅提升样本效率，这些结果表明通过点云对三维场景进行推理可以改善性能、缩短学习时间并提高机器学习算法的稳健性。

点云模型提升机器学习机器人的视觉鲁棒性

Point Cloud Models Improve Visual Robustness in Robotic Learners

Learning competitive behaviors in multi-agent settings such as racing
requires long-term reasoning about potential adversarial interactions. This
paper presents Deep Latent Competition (DLC), a novel reinforcement learning
algorithm that learns competitive visual control policies through self-play in
imagination. The DLC agent imagines multi-agent interaction sequences in the
compact latent space of a learned world model that combines a joint transition
function with opponent viewpoint prediction. Imagined self-play reduces costly
sample generation in the real world, while the latent representation enables
planning to scale gracefully with observation dimensionality. We demonstrate
the effectiveness of our algorithm in learning competitive behaviors on a novel
multi-agent racing benchmark that requires planning from image observations.
Code and videos available at
this https URL

该论文介绍了一种名为 Deep Latent Competition（DLC）的强化学习算法，其可以通过自我博弈在想象中学习竞争性视觉控制策略，从而实现长期推理。DLC 代理人在学习的世界模型的紧凑潜在空间中想象多智能体互动序列以减少实际采样生成的成本，同时潜在表示启用规划随着观察维度的扩展而平滑扩展。该算法在需要从图像观察中进行规划的新颖多智能体比赛基准测试中学习了有效的竞争行为。