CAREL：基于跨模态辅助目标的指令引导强化学习
CAREL: Instruction-guided reinforcement learning with cross-modal auxiliary objectives
AI总结：
本文提出CAREL框架，通过跨模态辅助损失和指令跟踪方法，提升语言引导目标达成强化学习的样本效率与泛化能力。
摘要：
将指令与环境进行 grounding 是解决语言引导的目标达成强化学习问题的关键步骤。在自动化强化学习中，一个关键关注点是增强模型在各种任务和环境中的泛化能力。在目标达成场景中，智能体必须理解指令中不同部分在环境上下文中的含义，以成功完成整体任务。在本工作中，我们提出 CAREL（跨模态辅助强化学习）作为解决该问题的新框架，该框架利用受视频-文本检索文献启发的辅助损失函数，以及一种名为指令跟踪的新方法，该方法自动跟踪环境中的进度。我们的实验结果表明，该框架在多模态强化学习问题中具有优越的样本效率和系统性泛化能力。我们的代码库可在此处获取。
英文摘要：
Grounding the instruction in the environment is a key step in solving language-guided goal-reaching reinforcement learning problems. In automated reinforcement learning, a key concern is to enhance the model's ability to generalize across various tasks and environments. In goal-reaching scenarios, the agent must comprehend the different parts of the instructions within the environmental context in order to complete the overall task successfully. In this work, we propose CAREL (Cross-modal Auxiliary REinforcement Learning) as a new framework to solve this problem using auxiliary loss functions inspired by video-text retrieval literature and a novel method called instruction tracking, which automatically keeps track of progress in an environment. The results of our experiments suggest superior sample efficiency and systematic generalization for this framework in multi-modal reinforcement learning problems. Our code base is available here.
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。
