LARG，基于语言的自适应奖励与目标生成
LARG, Language-based Automatic Reward and Goal Generation
AI总结：
本文提出LARG方法，利用大型语言模型将文本任务描述自动转换为奖励与目标生成函数，实现无需手工奖励的机器人操作策略可扩展训练。
摘要：
目标条件强化学习（GCRL）和多任务强化学习（MTRL）解决了与机器人学习相关的众多问题，包括运动、导航和操作场景。近期聚焦于语言定义的机器人操作任务的工作，导致了大量人工标注的繁琐生产，以创建与轨迹关联的文本描述数据集。为了利用基于文本任务描述的强化学习，我们需要以可扩展的方式为各个任务生成奖励函数。在本文中，我们利用大型语言模型（LLMs）的最新能力，引入了LARG，即基于语言的自适应奖励与目标生成，一种将基于文本的任务描述转换为其对应的奖励和目标生成函数的方法。我们评估了该方法在机器人操作中的应用，并展示了其以可扩展方式训练和执行策略的能力，无需手工设计的奖励函数。
英文摘要：
Goal-conditioned and Multi-Task Reinforcement Learning (GCRL and MTRL) address numerous problems related to robot learning, including locomotion, navigation, and manipulation scenarios. Recent works focusing on language-defined robotic manipulation tasks have led to the tedious production of massive human annotations to create dataset of textual descriptions associated with trajectories. To leverage reinforcement learning with text-based task descriptions, we need to produce reward functions associated with individual tasks in a scalable manner. In this paper, we leverage recent capabilities of Large Language Models (LLMs) and introduce \larg, Language-based Automatic Reward and Goal Generation, an approach that converts a text-based task description into its corresponding reward and goal-generation functions We evaluate our approach for robotic manipulation and demonstrate its ability to train and execute policies in a scalable manner, without the need for handcrafted reward functions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
