Deep Reinforcement Learning for Robotics

  • Deep Reinforcement Learning for Robotics
EEECS Summer Research Internships 2018

Proposed Project Title:

  • Deep Reinforcement Learning for Robotics

Principal Supervisor(s):
  • Vien Ngo


Project Description:

This project will investigate the use of deep reinforcement learning (DRL) to solve some simulated robotic locomotion tasks. The simulated robotic platform are provided by OpenAI Gym and Mujoco.

The project will also aim to propose novel ideas to improve the current state-of-the-art DRL methods. Proposed methods are expected to be more data-efficient and achieving higher performance.


Objectives:

The student will :

  • learn how to use python programming language, and get family with one of deep learning libraries (i.e. tensorflow)
  • learn reinforcement learning, one of machine learning method.
  • learn how to apply reinforcement learning for solving a practical problem, which is robotic tasks (on simulation).
  • get familiar with doing high-level researches by proposing an idea to improve state-of-the-art approaches.
  • write a report in the form of a research paper to summarize the work done.

Academic Requirements:

The scheme is open to all EEECS Undergraduates (apart from students on the BIT degree pathway and students who are due to graduate this summer)


General Information:

Each internship will last between 6-8 weeks and will pay a weekly stipend of £250.

Accommodation and travel costs are not provided under this scheme.

Start date: 1.7.2018

Duration:  8 (Weeks)

Location: Computer Science Building

Further information available at: http://www.qub.ac.uk/schools/eeecs/Research/


Contact details:

Supervisor Name: Dr. Vien Ngo
Address:

Queens University of Belfast
School of EEECS,
ECIT,
NI Science Park,
Queen’s Road,
Queen’s Island,
BT3 9DT

Email: v.ngo@qub.ac.uk
Tel: +44 (0)28 9097 1824