Reinforcement Learning: the Sooner the Better, or the Later the Better?
Shitian ShenMin ChiPublished in: UMAP (2016)
Keyphrases
- reinforcement learning
- function approximation
- model free
- state space
- robot control
- reinforcement learning algorithms
- machine learning
- control problems
- optimal policy
- reinforcement learning methods
- dynamic programming
- temporal difference
- direct policy search
- least squares
- robotic control
- data mining
- learning algorithm
- artificial intelligence
- optimal control
- markov decision processes
- support vector
- learning problems
- continuous state
- policy search
- relational reinforcement learning
- transfer learning