Reinforcement Learning with Generalizable Gaussian Splatting

arXiv:2404.07950v1 Announce Type: cross
Abstract: An excellent representation is crucial for reinforcement learning (RL) performance, especially in vision-based reinforcement learning tasks. The quality of the environment representation directly influences the achievement of the learning task. Previous vision-based RL typically uses explicit or implicit ways to represent environments, such as images, points, voxels, and neural radiance fields. However, these representations contain several drawbacks. They cannot either describe complex local geometries or generalize well to unseen scenes, or require precise foreground masks. …

abstract achievement arxiv cs.ai cs.cv cs.lg environment environments images performance quality reinforcement reinforcement learning representation tasks the environment type vision