Balancing exploration and exploitation in reinforcement learning using a value of information criterion.
Isaac J. SledgeJosé C. PríncipePublished in: ICASSP (2017)
Keyphrases
- balancing exploration and exploitation
- information criterion
- reinforcement learning
- model selection
- cross validation
- probability model
- learning to rank
- bayesian information criterion
- sample size
- state space
- widely applicable
- factor analysis
- machine learning
- lower bound
- free energy
- bayesian networks
- learning algorithm