Global Convergence of Policy Gradient Methods in Reinforcement Learning, Games and Control.
Shicong CenYuejie ChiPublished in: CoRR (2023)
Keyphrases
- global convergence
- learning games
- optimization methods
- global optimum
- convergence speed
- convergence rate
- policy gradient methods
- control system
- reinforcement learning
- augmented reality
- mixed reality
- learning platform
- robotic systems
- natural actor critic
- video games
- optimal control
- mobile learning
- particle swarm
- software engineering