Paper Title Number 3
Published in Journal 1, 2015
Recommended citation: Your Name, You. (2015). "Paper Title Number 3." Journal 1. 1(3). http://academicpages.github.io/files/paper3.pdf
This paper is about the number 3. The number 4 is left for future work.
Recommended citation: Your Name, You. (2015). “Paper Title Number 3.” Journal 1. 1(3).
* Multicriteria reinforcement learning (Betreuer: Xudong Sun)
A classical reinforcement learning agent tries to optimize a value function and adapt its behavior with policy iteration and balance the exploitation and exploration trade off with a probability sampling. However, it would be smarter to optimize several objective functions simultaneously. In this project, you will learn how to do bayesian optimization in a multi-criteria sense in the application scenario of reinforcement learning.
* Semantic web for machine learning and Conditional Random Field for code completion (Betreuer: Xudong Sun)
A knowledge graph in the form of semantic web will be created to help the user buid a machine learning pipeline which will also utilize CRF models for automatic code completion. See Big code. You will build a model to predict what will be the next line of code.