主要研究 今天

在不断扩展的机器学习世界里, 在强化学习方面已经有了积极的突破, a computer-based method focused on rewarding desired behaviors and punishing undesired ones.

然而, challenges remain when it comes to applying reinforcement learning to important real-world scenarios in which catastrophic failure is unacceptable.

为了解决这些问题, Marek Petrik, 计算机科学助理教授, was awarded a prestigious Faculty Early Career Development Program, 或职业, 获得了美国国家科学基金会的奖励. 派特里克会利用这五年, $575,866 award to conduct theoretical and algorithmic research with his 主要研究 students and collaborators from academic institutions and industrial research labs.

“I am very excited that I will be able to work on this project because I am passionate about this research,派特里克说, 谁研究强化学习很多年了. “在我看来，这个项目采取了一个新的、有前途的方向.”

Reinforcement algorithms are designed to perceive and interpret their environments, 采取行动，从尝试和错误中学习. Petrik说在某些领域, 比如棋盘游戏, 电子游戏和, 最近, 芯片布局设计, 强化学习已经取得了令人印象深刻的成就. 然而, 很难将它们转化为许多物理领域, 比如医疗保健或农业. One of the main reasons is that the existing algorithms are fragile and can fail catastrophically without a warning.

“This work will lead to algorithms that can avoid or at least detect that the learned policy, 或行动, 很可能会失败,派特里克说. “This project develops new reinforcement learning algorithms that achieve reliability by carefully balancing the expected quality of recommended decisions with their risk of failure.”

Petrik说传感器的改进, data collection and computational power have driven the desire to harness data to improve decision-making in various domains, 比如精准农业或医学. 他期待着新的, reliable algorithms will help bring data-driven decision-making to these new domains and plans to integrate the research with educational activities to provide graduate and undergraduate students with training opportunities and new study materials, 包括一本教科书.