This project is mainly used to reproduce the result in the paper of "Multi-objective Bandits: Optimizing the Generalized Gini Index"
The code should be run in anaconda 3 and the package of cvxopt is needed.
In order to draw figures similar to Fig 2 in the paper, some parameters in the file of LearningML.py should be revised, the list of these parameters is listed as follows:
- K the number of arms
- D the number of dimentions
- learn_Rate Learning_rate
- Iteration_num number of iterations in MO-OGDE and MO-LP
Reference: Busa-Fekete, Robert, et al. "Multi-objective Bandits: Optimizing the Generalized Gini Index." arXiv preprint arXiv:1706.04933 (2017).