This is the regularly updated webpage of Wendelin Böhmer's research group within the Sequential Decision Making group at the Delft University of Technology. The lab investigates cutting edge problems in Deep Reinforcement Learning (RL) with the goal to make RL applicable to real life. Check out our mission statement under Research, find out what our team is working on under People, or have a look at the courses and thesis opportunities we offer to TU Delft students under Teaching and Theses.

News

26-06-2024: Saray's paper Safe and stable motion primitives via imitation learning and geometric fabrics has been accepted to the RSS 2024 workshop Priors4Robots. Congratulations!
18-06-2024: Grigorii's paper You Shall Pass: Dealing with the Zero-Gradient Problem in Predict and Optimize for Convex Optimization has been accepted to the ICML 2024 workshop Differentiable Almost Everything. Congratulations!
12-06-2024: We submitted 3 papers to the European Workshop on Reinforcement Learning (EWRL 2024)! Thanks to Yaniv, Max and Laurens for their hard work.
02-05-2024: Our paper To the Max: Reinventing Reward in Reinforcement Learning has been accepted at the International Conference on Machine Learning (ICML 2024). Congratulations Grigorii!
02-02-2024: Grigorii has submitted two papers to the International Conference on Machine Learning (ICML 2024).
17-01-2024: Ksenija submitted a paper to the 33rd International Joint Conference on Artificial Intelligence (IJCAI 2024).
16-01-2024: Our paper Diverse Projection Ensembles for Distributional Reinforcement Learning has been accepted to the International Conference on Learning Representations (ICLR 2024). Congratulations to Moritz!
14-11-2023: The course Deep Reinforcement Learning (CS4400) starts today.
19-10-2023: Our paper Multi-Robot Local Motion Planning Using Dynamic Optimization Fabrics has been accepted to the 4th International Symposium on Multi-Robot and Multi-Agent Systems (MRS 2023). Congratulations to Saray!
21-07-2023: All 3 EWRL submissions were accepted! Congratulations to Max (paper), Moritz (paper) and Yaniv (paper)!
20-07-2023: Our paper Learning Scalable and Modular Efficient Communication for Multi-Robot Collision Avoidance has been accepted to the International Journal of Robotics Research (IJRR). Congratulations to Álvaro!
08-07-2023: Saray has submitted a paper to the 4th International Symposium on Multi-Robot and Multi-Agent Systems (MRS 2023).
07-06-2023: Our team submitted 3 papers to the European Workshop on RL (EWRL)! Thanks to Max, Moritz and Yaniv for their hard work.
17-05-2023: Our team submitted 3 papers to NeurIPS 2023! Thanks to Grigorii, Moritz and Yaniv for all their hard work.
11-04-2023: Our paper Active Classification of Moving Targets with Learned Control Policies has been accepted by IEEE Robotics and Automation Letters (RA-L). Congratulations to Álvaro Serra-Gómez!
31-01-2023: PhD vacancy Reliable Out-of-Distribution Generalization in Deep Reinforcement Learning is online (but now closed)!
23-12-2022: NWO project proposal Reliable Out-of-Distribution Generalization in Deep Reinforcement Learning has been accepted! An open PhD position will be announced soon.
15-11-2022: We welcome Saray Bakker as a new PhD student to the lab!
15-11-2022: The course Deep Reinforcement Learning (CS4400, now in Q2!) starts today.
01-11-2022: We welcome Yaniv Oren as a new PhD student to the lab!
01-09-2022: We welcome Laurens Engwegen as a new PhD student to the lab!
15-02-2022: We welcome Max Weltewrede as a new PhD student to the lab!
08-02-2022: The course Deep Reinforcement Learning (CS4400) starts for the first time today.