Coordinate Ascent for Off-Policy RL with Global Convergence Guarantees.

Hsin-En Su Yen-Ju Chen Ping-Chun Hsieh Xi Liu

Published in: AISTATS (2023)

Keyphrases

coordinate ascent
global convergence
reinforcement learning
global optimum
convergence rate
convergence analysis
optimization methods
convergence speed
convex minimization
simulated annealing
hybrid algorithm
particle swarm
search space
multi objective
image recovery