The multi-armed bandit problem is a class example to demonstrate the exploration versus exploitation dilemma. This post introduces the bandit problem and how to solve it using different exploration strategies.

Huawei Noah’s Arc Lab Recuiring Long-Term Interns

[What] Deep Learning and Reinforcement Learning for Supply Chain Management and Combinatorial Optimization

[Who] Master or PhD students

[Where] Hong Kong or Shenzhen

[How Long] Longer than 6 months

[Salary] Confidential

[Requirements]
[Necessary]
(0) Graduated from Computer Science is preferred, persons from other departments should have coding experience.
(1) Strong skills in coding (python/C/C++), familiar with deep learning frameworks, e.g., Tensorflow, Pytorch, etc.
(2) Familiar the papers on corresponding top conference
(3) Quickly reproduce the codes from top conference.
[Extra points]
(1) 1-st author, or main co-author to publish papers on ccf b/a conference
(2) Familiar with discrete optimization, integer programming, or combinatorial optimization
(3) Experience in supply chain management, e.g., scheduling, manufacturing planning and bin-packing.
If you are interested in this position, please contract xijun.li@huawei.com and huilzhen@um.cityu.edu.hk. Any interns have extremely possibilities to work as a fulltime research scientist/engineer in Noah or Huawei.