CAREER: Towards Real-world Reinforcement Learning

职业：走向现实世界的强化学习

• 批准号: 2339395
• 负责人: Wen Sun
• 金额: $ 60万
• 依托单位: Cornell University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2024
• 资助国家: 美国
• 起止时间: 2024-03-01 至 2029-02-28
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2339395&HistoricalAwards=false
• 关键词: CAREER; Towards; Real; world; Reinforcement

Reinforcement learning (RL) is one of the most important paradigms for modeling data-driven decision-making. Recent years have witnessed several empirical successes of RL, such as RL agents that outperform humans in video and board games. However, many empirical RL algorithms today often require many training examples to learn and can produce unreliable solutions (solutions that exhibit catastrophic failures, for example). While these issues are typically not problematic when training RL agents in simulators, they pose significant difficulties when deploying RL to real-world problems where data (including human feedback) is expensive, and reliability is essential. The main novelty of this project will be the development of new RL algorithms that can learn efficiently (from as few training data points as possible) and reliably (avoid catastrophic failures with high probability). The development of such RL algorithms can expand the applications of RL systems from simulation to real-world applications where data is expensive to collect and safety is critical. In autonomous driving, the developed technologies can make self-driving cars adapt to new road conditions safely by making fewer mistakes. In generative Artificial Intelligence (AI), efficient and reliable RL algorithms that can learn from rich human feedback will enable better human-AI alignment, making AI systems improve reliably and safely under human guidance.The main research goal of this project is to enable real-world RL by advancing RL techniques, theoretically and empirically. The critical innovation in the project is to develop safe and efficient RL algorithms by leveraging specific problem structures and rich human feedback. The project has three main thrusts. First, the project will establish risk-averse RL algorithms that are provably correct and scalable to high dimensional data. Second, the project will develop RL algorithms that can leverage common problem-specific structures for improved sample efficiency. Third, the project will create new algorithms for RL with rich feedback beyond scalar rewards (including preference-based feedback and positive demonstrations). In addition to the proposed work on algorithmic advancements, the project will focus on their deployment to real-world problems, including database query optimization and optimizing generative models such as Large Language Models and Diffusion Models.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

强化学习（RL）是数据驱动决策建模的最重要范式之一。近年来，RL已经取得了一些经验性的成功，例如RL代理在视频和棋盘游戏中的表现超过了人类。然而，今天的许多经验RL算法通常需要许多训练示例来学习，并且可能产生不可靠的解决方案（例如，表现出灾难性故障的解决方案）。虽然在模拟器中训练RL代理时，这些问题通常不会成为问题，但在将RL部署到数据（包括人类反馈）昂贵且可靠性至关重要的现实问题时，它们会带来重大困难。该项目的主要新奇将是开发新的RL算法，这些算法可以有效地（从尽可能少的训练数据点）和可靠地（避免高概率的灾难性故障）学习。这种RL算法的开发可以将RL系统的应用从仿真扩展到真实世界的应用，其中数据收集昂贵且安全性至关重要。在自动驾驶方面，所开发的技术可以使自动驾驶汽车通过更少的错误安全地适应新的路况。在生成式人工智能（AI）中，可以从丰富的人类反馈中学习的高效可靠的强化学习算法将实现更好的人类-AI对齐，使AI系统在人类指导下可靠安全地改进。本项目的主要研究目标是通过理论和经验上推进强化学习技术来实现现实世界的强化学习。该项目的关键创新是通过利用特定的问题结构和丰富的人类反馈来开发安全有效的RL算法。该项目有三个主要目标。首先，该项目将建立可证明正确并可扩展到高维数据的风险规避RL算法。其次，该项目将开发RL算法，可以利用常见的特定问题结构来提高样本效率。第三，该项目将为RL创建新的算法，并提供超越标量奖励的丰富反馈（包括基于偏好的反馈和积极的演示）。除了在算法改进方面的建议工作外，该项目还将专注于将其部署到现实世界的问题中，包括数据库查询优化和优化生成模型，如大型语言模型和扩散模型。该奖项反映了NSF的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。