Collaborative: RI: Feature Discovery and Benchmarks for Exportable Reinforcement Learning

协作：RI：可导出强化学习的特征发现和基准

• 批准号: 0713435
• 负责人: Ronald Parr
• 金额: $ 22.5万
• 依托单位: Duke University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2007
• 资助国家: 美国
• 起止时间: 2007-10-01 至 2011-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0713435&HistoricalAwards=false
• 关键词: Collaborative; RI; Feature; Discovery; Benchmarks

Collaborative Proposal pair: 0713435 (Lead) & 0713148"Collaborative: RI: Feature Discovery and Benchmarks for exportable Reinforcement Learning"PI: Ronald Parr, Duke UniversityPI: Michael L. Littman, Rutgers UniversityABSTRACTThis project focuses on several aspects of automated feature discovery in the context of reinforcement learning. Badly chosen features cause reinforcement-learning algorithms to fail and, as such, only individuals skilled in feature construction can create successful reinforcement-learning systems for novel tasks. This issue underscores two shortcomings in existing research. First, most existing reinforcement-learning methods cannot generate or discover features automatically and robustly. Second, existing benchmark problems and paradigms for benchmarking do not distinguish adequately between clever algorithm design and clever feature engineering.This project addresses these challenges in two-pronged approach. The first prong aims to advance a technical agenda leading to a new approach to feature discovery and model representation. The second prong is the development of a benchmark methodology and repository with a different focus and structure from existing endeavors. The goal for the benchmarking effort will be to produce a set of fair and reproducible experiments that will help elucidate the strengths and weaknesses of existing approaches, while simultaneously introducing challenges to motivate the development of new approaches.

Collaborative Proposal pair: 0713435 (Lead) & 0713148"Collaborative: RI: Feature Discovery and Benchmarks for exportable Reinforcement Learning"PI: Ronald Parr, Duke UniversityPI: Michael L. Littman, Rutgers UniversityABSTRACTThis project focuses on several aspects of automated feature discovery in the context of reinforcement learning.不良选择的功能会导致加强学习算法失败，因此，只有熟练的特征构造的个人才能为新任务创建成功的加强学习系统。这个问题强调了现有研究中的两个缺点。首先，大多数现有的增强学习方法无法自动，稳健地生成或发现功能。其次，现有的基准问题和基准测试范例不能在聪明的算法设计和聪明的功能工程之间充分区分。该项目以两种挑剔的方法解决了这些挑战。第一个插脚旨在推进技术议程，从而提出一种新的发现和模型表示的方法。第二阶段是开发基准方法和存储库，其重点和结构与现有努力不同。基准努力的目标是制作一套公平且可重复的实验，以帮助阐明现有方法的优势和劣势，同时引入挑战以激发新方法的发展。