C.T. Ponnambalam (2023), Abstraction-Guided Modular Reinforcement Learning, PhD Thesis Delft University of Technology.

Danial Kamran, Thiago D. Simão, Qisong Yang, Canmanie T. Ponnambalam, Johannes Fischer, Matthijs T.J. Spaan, Martin Lauer (2022), A Modern Perspective on Safe Automated Driving for Different Traffic Dynamics using Constrained Reinforcement Learning, In Proceedings of the IEEE International Conference on Intelligent Transportation Systems p.4017-4023, IEEE.

Canmanie Ponnambalam, Danial Kamran, Thiago D. Simão, Frans A. Oliehoek, Matthijs T.J. Spaan (2022), Back to the Future: Solving Hidden Parameter MDPs with Hindsight.

C.T. Ponnambalam, F.A. Oliehoek, M.T.J. Spaan (2021), Abstraction-Guided Policy Recovery from Expert Demonstrations, In 31th International Conference on Automated Planning and Scheduling p.560-568, American Association for Artificial Intelligence (AAAI).

Jordi Smit, Canmanie Ponnambalam, Matthijs T.J. Spaan, Frans A. Oliehoek (2021), PEBL: Pessimistic Ensembles for Offline Deep Reinforcement Learning, In Robust and Reliable Autonomy in the Wild Workshop at the 30th International Joint Conference of Artificial Intelligence.

C.T. Ponnambalam, F.A. Oliehoek, M.T.J. Spaan (2020), Abstraction-Guided Policy Recovery from Expert Demonstrations.

Greg Neustroev, Canmanie Ponnambalam, Mathijs de Weerdt, Matthijs Spaan (2020), Interval Q-Learning: Balancing Deep and Wide Exploration, In Adaptive and Learning Agents Workshop.