Feature Reinforcement Learning using Looping Suffix Trees.
Mayank DaswaniPeter SunehagMarcus HutterPublished in: EWRL (2012)
Keyphrases
- suffix tree
- reinforcement learning
- data structure
- hidden state
- suffix array
- pattern matching
- space requirements
- string matching
- function approximation
- data sets
- hidden markov models
- markov decision processes
- image features
- state space
- database systems
- decision trees
- information retrieval
- query processing
- feature vectors
- relational databases
- machine learning