Publications

PhD research line (the intersection of reinforcement learning and planning)

Moerland TM, Broekens J, Jonker CM. Model-based Reinforcement Learning: A Survey. 2020.  In submission.  (PDF)

Moerland TM, Broekens J, Jonker CM. A Framework for Reinforcement Learning and Planning. 2020.  In submission.  (PDF)

Moerland TM, Deichler A, Baldi S, Broekens J, Jonker CM. Think Neither Too Fast Nor Too Slow: The Computational Trade-off Between Planning And Reinforcement Learning. 2020. Bridging the gap between planning and reinforcement learning workshop @ ICAPS. (PDF)

Moerland TM, Broekens J, Plaat A, Jonker CM. A0C: Alpha Zero in Continuous Action Space. 2018.  Planning and Learning (PAL) Workshop @ ICML 2018. (PDF)

Moerland TM, Broekens J, Plaat A, Jonker CM. Monte Carlo Tree Search for Asymmetric Trees. 2018.  Planning and Learning (PAL) Workshop @ ICML 2018. (PDF)

Moerland TM, Broekens J, Jonker CM. The Potential of the Return Distribution for Exploration in RL. 2018. Exploration in Reinforcement Learning Workshop @ ICML 2018. . (PDF)

Moerland TM, Broekens J, Jonker CM. Efficient Exploration with Double Uncertain Value Networks. Deep Reinforcement Learning Symposium @ Conference on Neural Information Processing Systems (NIPS). 2017. (PDF)

Moerland TM, Broekens J, Jonker CM. Learning Multimodal Transition Dynamics for Model-Based Reinforcement Learning. Scaling Up Reinforcement Learning (SURL) Workshop @ European Conference on Machine Learning (ECML). 2017. (PDF) (Code) (Slides)

 

Other topics

Moerland TM, Broekens J, Jonker CM. Emotion in Reinforcement Learning Agents and Robots: A Survey.  Machine Learning 107(2), 443-480. 2017. (PDF)

W. J. Wolfslag, M. Bharatheesha, T. M. Moerland and M. Wisse. RRT-CoLearn: Towards Kinodynamic Planning Without Numerical Trajectory Optimization. IEEE Robotics and Automation Letters, vol. 3, no. 3, pp. 1655-1662, July 2018. (PDF)

Janmaat VT, Kortekaas KE, Moerland TM, Vereijken MWC, Schoones JW, Hylckama Vlieg A, Dekker FW. Research-Tutored Learning: An Effective Way for Students to Benefit Research by Critical Appraisal. Medical Science Educator. 2013. (PDF)

Wolfslag WJ, Bharatheesha M, Moerland TM, Wisse M. RRT-CoLearn: towards kinodynamic planning without numerical trajectory optimization. International Conference on Robotics and Automation (ICRA).  2018. (PDF)

Moerland TM, Broekens J, Jonker CM. Fear and Hope Emerge From Anticipation in Model-Based Reinforcement Learning.  International Joint Conference on Artificial Intelligence (IJCAI). 2016. (PDF)

Moerland TM, Chandarr A, Rudinac M and Jonker P. Knowing What You Don’t Know: Novelty Detection for Action Recognition in Personal Robots.  VISAPP. 2016. (PDF)

 

Abstracts / Misc

Moerland TM, Broekens J, Jonker CM. Learning Multimodal Transition Dynamics for Model-Based Reinforcement Learning: Abstract. Benelux Conference on Artificial Intelligence (BNAIC). 2017. (PDF)

Moerland TM. Efficient Exploration with Uncertain Value Networks. Delft Workshop on Robot Learning. 2017. (PDF)

Bharatheesha M, Wolfslag W, Moerland TM. A dataset bias problem for learning-RRT, with two potential solutions. Delft Workshop on Robot Learning. 2017. (PDF)

Moerland TM. Nieuwheidsdetectie voor Activiteit Herkenning door Robots. STAtOR. 2017. (PDF) (Dutch)

Wolfslag WJ, Bharatheesa M, Moerland TM, Wisse M. Learning indirect optimal control for dynamic motion planning with RRT.  Dynamic Walking. 2017. (PDF)

Moerland TM, Broekens J, Jonker CM. Hope and Fear in Reinforcement Learning Agents: Extended Abstract. Benelux Conference on Artificial Intelligence (BNAIC). 2016. (PDF)

This is a test a = b^2