Reinforcement Learning With Adaptive Policy Gradient Transfer Across Heterogeneous Problems.
Gengzhi ZhangLiang FengYu WangMin LiHong XieKay Chen TanPublished in: IEEE Trans. Emerg. Top. Comput. Intell. (2024)
Keyphrases
- reinforcement learning
- policy gradient
- control problems
- actor critic
- optimization problems
- function approximation
- reinforcement learning methods
- reinforcement learning algorithms
- policy search
- transfer learning
- function approximators
- solving problems
- optimal control
- learning capabilities
- radial basis function
- search space
- search algorithm