392267 Learning to Act - Reinforcement Learning with Deep Neural Networks in Simulated Environments (Pj) (WiSe 2018/2019)

For more information about the project, please contact
Dr. Andrew Melnik anmelnik(at)techfak.uni-bielefeld.de
Office 3.308 (CITEC Building)
Consultation hours: Wednesdays 17:15-18:00

The project intends to gain practical experience with Deep Reinforcement Learning [1]. In this project, you will apply neural networks to learn and produce complex purposeful actions in simulated environments in the context of: robotic environments [2, 3], bipedal locomotion [4], six-legged robot, and/or computer games [5, 6, 7]:
[1] https://youtu.be/XjsY8-P4WHM
[2] https://blog.openai.com/ingredients-for-robotics-research
[3] https://youtu.be/0og1SaZYtRc
[4] https://www.crowdai.org/challenges/nips-2018-ai-for-prosthetics-challenge
[5] http://vizdoom.cs.put.edu.pl
[6] https://www.pommerman.com/competitions
[7] https://gym.openai.com/envs/MontezumaRevenge-v0

Please note that the teams will be selected by the supervisors on the basis of short applications that students are expected to send to them. Registering to the project in the ekVV will only be regarded as expression of interest; it will not secure a team membership.
Please get in touch with the supervisors for information on the application procedure.

Requirements for participation, required level

Required skills:
- Introduction to Neural Networks course or Advanced Neural Networks
- Python (>= 1 year)