Policy Optimization as Online Learning with Mediator Feedback.
Alberto Maria MetelliMatteo PapiniPierluca D'OroMarcello RestelliPublished in: CoRR (2020)
Keyphrases
- online learning
- optimization process
- optimization algorithm
- online course
- global optimization
- relevance feedback
- combinatorial optimization
- e learning
- active learning
- distance learning
- optimization problems
- distance education
- optimization method
- higher education
- blended learning
- learning algorithm
- databases
- neural network
- constrained optimization
- optimization methods
- optimal policy
- cost function
- feature space
- machine learning