Improving Reinforcement Learning by Using Case Based Heuristics.
Reinaldo A. C. BianchiRaquel RosRamón López de MántarasPublished in: ICCBR (2009)
Keyphrases
- reinforcement learning
- case based reasoning
- function approximation
- heuristic search
- machine learning
- search algorithm
- reinforcement learning algorithms
- markov decision processes
- model free
- information retrieval
- data sets
- heuristic rules
- state space
- model based reasoning
- temporal difference
- learning tasks
- supervised learning
- scheduling problem
- dynamic programming
- expert systems