Hamilton-Jacobi Reachability in Reinforcement Learning: A Survey.

Milan Ganai Sicun Gao Sylvia L. Herbert

Published in: CoRR (2024)

Keyphrases

hamilton jacobi
reinforcement learning
state space
finite difference
medial axis
partial differential equations

level set method
function approximation
eikonal equation
optimal policy
reinforcement learning algorithms
actor critic

model free
markov decision processes
dynamic programming
machine learning
natural images
temporal difference

learning algorithm
optimal control
higher order
partially observable markov decision processes
feature vectors
computer vision