Dr Thommen George Karimpanal

Deakin University

Thommen is a Lecturer at Deakin University. His research interests lie in the field of reinforcement learning, and in improving its sample efficiency by leveraging available context, be it in the form of domain priors, knowledge from humans or other agents in the loop and/or inferring patterns from the environment itself. Overall, his research aims to develop efficient, aligned and practically deployable algorithms.

Institution Profile

Personal Website

ARAAC Publications

M. Hussonnois, T. G. Karimpanal, M. S. Jha, S. Rana (2025). Human-informed skill discovery: Controlled diversity with preference in reinforcement learning Expert Systems with Applications
M. Hussonnois, T. G. Karimpanal, S. Rana (2025). Human-Aligned Skill Discovery: Balancing Behaviour Exploration and Alignment International Conference on Autonomous Agents and Multiagent Systems (AAMAS)
A. Shereef Palattuparambil, T. G. Karimpanal, S. Rana (2024). Personalisation via Dynamic Policy Fusion International Conference on Human-Agent Interaction (HAI)
M. Senadeera, T. G. Karimpanal, S. Jacobs, S. Gupta, S. Rana (2024). EMOTE: An Explainable Architecture for Modelling the Other through Empathy International Joint Conference on Artificial Intelligence (IJCAI)
F. Cruz, T. G. Karimpanal, M. A. Solis, P. Barros, R. Dazeley (2023). Human-aligned reinforcement learning for autonomous agents and robots Neural Computing and Applications
T. G. Karimpanal, S. Rana, S. Gupta, T. Tran, S. Venkatesh (2020). Learning Transferable Domain Priors for Safe Exploration in Reinforcement Learning International Joint Conference on Neural Networks (IJCNN)
T. G. Karimpanal, E. Wilhelm (2017). Identification and off-policy learning of multiple objectives using adaptive clustering Neurocomputing