Autonomous Valet Parking with Asynchronous Advantage Actor-Critic Proximal Policy Optimization.
Teckchai TiongIsmail SaadKenneth Tze Kin TeoHerwansyah Bin LagoPublished in: CCWC (2022)
Keyphrases
- actor critic
- policy gradient
- reinforcement learning
- temporal difference
- approximate dynamic programming
- gradient method
- optimal control
- policy gradient methods
- neuro fuzzy
- policy iteration
- optimization problems
- reinforcement learning algorithms
- natural actor critic
- function approximation
- optimization algorithm
- optimization method
- markov decision processes
- evaluation function
- robust optimization
- control policy
- average reward
- machine learning
- linear programming
- optimization methods
- evolutionary algorithm
- linear program