Research Interests

My academic interests lie in the fields of reinforcement learning, life-long learning, bio-inspired learning algorithms and optimization applied to control problems. My current research focuses on the safe and sample-efficient training of reinforcement learning agents through the autonomous inference of domain priors, as well as other mechanisms that contribute towards the agent's domain-awareness.

News & Updates

I will be serving as guest editor for a special issue on Human-aligned RL in Neural Computing Applications (Springer):

April, 2021

Email: thommengk at gmail dot com

Other Avenues

Google Scholar


Localization, mapping, path planning and control

Object recognition using the EvoBot

Multiagent mapping application

EvoBot executing energy optimal navigation