Topology-Guided Modular Actor-Critic Learning for Continuous Systems under Temporal Objectives
A model-free actor-critic algorithm whose policy evaluation solves a constrained optimization problem by the augmented Lagrangian method, yielding hyperparameter self-tuning, and proves its optimality and convergence in the tabular case is presented.
Le-Ning Li, Zhentian Qian, Jianan Xia et al.
· 0 citations