This paper presents a novel method for learning reward functions for robotic
motions by harnessing the power of a CLIP-based model. Traditional reward
function design often hinges on manual feature engineering, which can struggle
to generalize across an array of tasks. Our approach circumvents this challenge
by capitalizing on CLIP's capability to process both state features and image
inputs effectively. Given a pair of consecutive observations, our model excels
in identifying the motion executed between them. We showcase results spanning
various robotic activities, such as directing a gripper to a designated target
and adjusting the position of a cube. Through experimental evaluations, we
underline the proficiency of our method in precisely deducing motion and its
promise to enhance reinforcement learning training in the realm of robotics.

利用基于 CLIP 的模型学习机器人运动的奖励函数的新方法，回避了传统奖励函数设计中的挑战，通过利用 CLIP 处理状态特征和图像输入的能力，准确识别连续观察之间的运动并增强机器人领域的强化学习培训。