CBR for State Value Function Approximation in Reinforcement Learning.
Thomas GabelMartin A. RiedmillerPublished in: ICCBR (2005)
Keyphrases
- state space
- reinforcement learning
- case based reasoning
- temporal difference learning
- optimal policy
- temporal difference
- state variables
- function approximation
- basis functions
- real time
- reinforcement learning algorithms
- case base
- markov decision processes
- machine learning
- data sets
- dynamical systems
- transfer learning
- evaluation function
- search space
- artificial intelligence
- partially observable
- function approximators
- state action
- database