Residual Sarsa algorithm with function approximation.
Qiming FuWen HuQuan LiuHeng LuoLingyao HuJianping ChenPublished in: Clust. Comput. (2019)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference learning
- learning algorithm
- mountain car
- dynamic programming
- model free
- convergence rate
- function approximators
- temporal difference
- real valued
- support vector machine svm
- search space
- text categorization
- evolutionary algorithm
- policy evaluation
- similarity measure