Continuous-action reinforcement learning with fast policy search and adaptive basis function selection.
Xin XuChunming LiuDewen HuPublished in: Soft Comput. (2011)
Keyphrases
- policy search
- basis functions
- continuous action
- reinforcement learning
- state space
- continuous state
- reinforcement learning algorithms
- linear combination
- dynamic programming
- radial basis function
- function approximation
- markov decision problems
- policy gradient
- multi agent
- neural network
- model free
- partially observable markov decision processes
- markov decision processes
- monte carlo
- markov chain
- search algorithm
- learning algorithm