Keyphrases
- reinforcement learning
- state space
- function approximation
- belief nets
- reinforcement learning algorithms
- reinforcement learning methods
- deep learning
- markov decision processes
- temporal difference
- optimal control
- bayesian framework
- optimal policy
- wide variety
- machine learning
- real world
- policy search
- robotic control
- model free
- prior knowledge
- learning algorithm
- learning classifier systems
- learning capabilities
- prior probabilities
- markov decision process
- multi agent
- case study
- stochastic approximation
- transition model
- website
- data mining