all AI news
Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical Systems
March 8, 2024, 5:41 a.m. | Wesley A. Suttle, Vipul K. Sharma, Krishna C. Kosaraju, S. Sivaranjani, Ji Liu, Vijay Gupta, Brian M. Sadler
cs.LG updates on arXiv.org arxiv.org
Abstract: We develop provably safe and convergent reinforcement learning (RL) algorithms for control of nonlinear dynamical systems, bridging the gap between the hard safety guarantees of control theory and the convergence guarantees of RL theory. Recent advances at the intersection of control and RL follow a two-stage, safety filter approach to enforcing hard safety constraints: model-free RL is used to learn a potentially unsafe controller, whose actions are projected onto safe sets prescribed, for example, by …
abstract advances algorithms arxiv control convergence cs.lg gap intersection math.oc reinforcement reinforcement learning safety sampling stage systems theory type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US