Meta-Learning Embeddings for Reinforcement Learning
Scope: Master’s Project/Master’s thesis
Advisor: Dr. Kevin S. Luck (kevin.s.luck@aalto.fi)
Added: 31.August 2022
Topic:
Meta-Learning of ‘learning-how-to-learn’ has been immensely popular in the deep learning community in recent years. In this thesis, we will investigate the problem of using meta-learning approaches and ideas to learn latent policy embeddings for use in reinforcement learning. A potential approach for this is hyper networks, ie networks which can generate other networks (see references). The thesis will investigate the application of these approaches and evaluate their usefulness in robot learning and continuous control tasks. Currently, the use of policy embeddings and hyper networks is an active area in research with potential applications to real-world robotics. This is a research-oriented thesis where the student will have the possibility to work on state-of-the-art problems and propose novel methods and algorithms for their use in robot learning. For further information, please contact the supervisor.
Minimum knowledge:
- Python
- Has taken a course in Machine Learning
- Willingness and motivation to explore and read research papers
Preferred knowledge:
- Has taken a robotics course (beneficial)
- Has taken a course about reinforcement learning or advanced machine learning (beneficial)
Thesis student will:
- Conduct a research project under guidance of the supervisor
- Learn to read and disseminate research papers
- Aquire skills in robot learning & reinforcement learning
Related Literature: