Deep Reinforcement Learning: An Overview.
Seyed Sajad MousaviMichael SchukatEnda HowleyPublished in: IntelliSys (2) (2016)
Keyphrases
- reinforcement learning
- function approximation
- model free
- state space
- optimal policy
- reinforcement learning algorithms
- temporal difference
- deep learning
- markov decision processes
- learning process
- learning algorithm
- databases
- robotic control
- robot control
- future trends
- control problems
- continuous state
- real time
- information retrieval
- policy search
- action selection
- autonomous learning
- direct policy search
- stochastic approximation
- temporal difference learning
- learning classifier systems
- optimal control
- data sets