阅读并收获回报：借助说明手册学习玩 Atari 游戏
Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals
AI总结：
针对强化学习样本效率低的问题，提出Read and Reward框架，通过阅读Atari游戏说明手册提取信息并生成辅助奖励，显著提升多种RL算法的性能与训练速度。
摘要：
高样本复杂度长期以来一直是强化学习（RL）面临的挑战。另一方面，人类不仅通过交互或演示来学习执行任务，还通过阅读非结构化文本文档（例如说明手册）来学习。说明手册和维基页面是最丰富的数据之一，它们可以为智能体提供有价值的特征、策略或特定任务的环境动态和奖励结构。因此，我们假设利用人类编写的说明手册来辅助学习特定任务策略的能力，应能带来更高效、性能更优的智能体。我们提出了“阅读并回报”（Read and Reward）框架。该框架通过阅读 Atari 游戏开发者发布的说明手册来加速 Atari 游戏上的强化学习算法。我们的框架包含一个问答提取模块，该模块从手册中提取并总结相关信息；以及一个推理模块，该模块基于手册中的信息评估对象与智能体之间的交互。当检测到交互时，会向标准的 A2C 强化学习智能体提供辅助奖励。实验表明，在我们的设计辅助下，各种强化学习算法在性能和训练速度上均获得了显著提升。
英文摘要：
High sample complexity has long been a challenge for RL. On the other hand, humans learn to perform tasks not only from interaction or demonstrations, but also by reading unstructured text documents, e.g., instruction manuals. Instruction manuals and wiki pages are among the most abundant data that could inform agents of valuable features and policies or task-specific environmental dynamics and reward structures. Therefore, we hypothesize that the ability to utilize human-written instruction manuals to assist learning policies for specific tasks should lead to a more efficient and better-performing agent. We propose the Read and Reward framework. Read and Reward speeds up RL algorithms on Atari games by reading manuals released by the Atari game developers. Our framework consists of a QA Extraction module that extracts and summarizes relevant information from the manual and a Reasoning module that evaluates object-agent interactions based on information from the manual. An auxiliary reward is then provided to a standard A2C RL agent, when interaction is detected. Experimentally, various RL algorithms obtain significant improvement in performance and training speed when assisted by our design.
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。
