A Single-Loop Deep Actor-Critic Algorithm for Constrained Reinforcement Learning with Provable Convergence.
Kexuan WangAn LiuBaishuo LiuPublished in: CoRR (2023)
Keyphrases
- actor critic
- reinforcement learning
- convergence proof
- dynamic programming
- cost function
- learning algorithm
- particle swarm optimization
- policy gradient
- computational complexity
- monte carlo
- convergence rate
- natural actor critic
- machine learning
- reinforcement learning algorithms
- simulated annealing
- approximate dynamic programming
- optimal solution