首页|Investigators from Indian Institute of Science Zero in on Robotics and Automation (Funnel-based Reward Shaping for Signal Temporal Logic Tasks In Reinforcement Learning)
Investigators from Indian Institute of Science Zero in on Robotics and Automation (Funnel-based Reward Shaping for Signal Temporal Logic Tasks In Reinforcement Learning)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
IEEE
Research findings on Robotics - Robotics and Automation are discussed in a new report. According to news reporting from Bangalore, India, by NewsRx journalists, research stated, "Signal Temporal Logic (STL) is a powerful framework for describing the complex temporal and logical behaviour of the dynamical system." Financial support for this research came from Google and SERB Research Grants. The news correspondents obtained a quote from the research from the Indian Institute of Science, "Numerous studies have attempted to employ reinforcement learning to learn a controller that enforces STL specifications; however, they have been unable to effectively tackle the challenges of ensuring robust satisfaction in continuous state space and maintaining tractability. In this letter, leveraging the concept of funnel functions, we propose a tractable reinforcement learning algorithm to learn a time-dependent policy for robust satisfaction of STL specification in continuous state space." According to the news reporters, the research concluded: "We demonstrate the utility of our approach on several STL tasks using different environments." This research has been peer-reviewed.
BangaloreIndiaAsiaRobotics and AutomationRoboticsEmerging TechnologiesMachine LearningReinforcement LearningIndian Institute of Science
NETL
NSTL
IEEE
