Blar i SINTEF Open på tidsskrift "Frontiers in Artificial Intelligence and Applications"
Viser treff 1-1 av 1
-
Safe Reinforcement Learning for Continuous Spaces through Lyapunov-Constrained Behavior
(Journal article; Peer reviewed, 2011)This paper presents a safe learning strategy for continuous state and action spaces by utilizing Lyapunov stability properties of the studied systems. The reinforcement learning algorithm Continous Actor-Critic Learning ...