Algorithms for Learning Markov Field Policies.
Abdeslam BoulariasOliver KroemerJan PetersPublished in: NIPS (2012)
Keyphrases
- learning algorithm
- learning process
- noise tolerant
- learning tasks
- learning systems
- learning models
- computational cost
- theoretical analysis
- neural network
- policy gradient methods
- markov model
- orders of magnitude
- online learning
- supervised learning
- data sets
- knowledge acquisition
- optimization problems
- mobile learning
- learning problems
- active learning
- machine learning
- data mining