Under review
- Engwegen, L.; Brinks, D. and Böhmer, W. Generalisation to unseen topologies: Towards control of biological neural network activity. Submitted to the European Workshop on Reinforcement Learning (EWRL 2024).
- Weltevrede, M.; Kaubek, F.; Spaan, M.T.J. and Böhmer, W. Explore-Go: Leveraging Exploration for Generalisation in Deep Reinforcement Learning. Submitted to the European Workshop on Reinforcement Learning (EWRL 2024).
- Oren, Y.; Zanger, M.A; Van der Vaart, P.R.; Spaan, M.T.J. and Böhmer, W. Value Improved Actor Critic Algorithms. Submitted to Neural Information Processing Systems (NeurIPS 2024) and to the European Workshop on Reinforcement Learning (EWRL 2024).
- Stepanovic, K.; Böhmer, W. and de Weerdt, M. A Penalty-Based Guardrail Algorithm for Non-Decreasing Optimization with Inequality Constraints. Submitted to the European Conference on Artificial Intelligence (ECAI 2024).
2024
- Veviurko, G.; Böhmer, W. and de Weerdt, M. (2024, ICML). To the Max: Reinventing Reward in Reinforcement Learning. Proceedings of the International Conference on Machine Learning.
- Zanger, M.A.; Böhmer, W., and Spaan M.T.J. (2024, ICLR). Diverse Projection Ensembles for Distributional Reinforcement Learning. Proceedings of the International Conference on Learning Representations.
- Casao, S., Serra-Gómez, Á., Murillo, A.C., Böhmer, W., Alonso-Mora, J., and Montijano, E. (2024). Distributed multi-target tracking and active perception with mobile camera networks. Computer Vision and Image Understanding, Volume 238, January 2024, 103876, DOI:10.1016/j.cviu.2023.103876.
- Veviurko, G.; Böhmer, W. and de Weerdt, M. (2024, ICML workshop) You Shall Pass: Dealing with the Zero-Gradient Problem in Predict and Optimize for Convex Optimization. ICML 2024 workshop Differentiable Almost Everything.
- Bakker, S.; Pérez-Dattari, R.; Santina, C.D.; Böhmer, W. and Alonso-Mora, J. (2024, RSS workshop). Safe and stable motion primitives via imitation learning and geometric fabrics. RSS 2024 workshop Priors4Robots.
2023
- Serra-Gómez, Á., Zhu, H., Brito, B., Böhmer, W., Alonso-Mora, J. (2023). Learning Scalable and Modular Efficient Communication for Multi-Robot Collision Avoidance. Autonomous Robots.
- Serra-Gómez, Á., Montijano, E., Böhmer, W., Alonso-Mora, J. (2023). Active Classification of Moving Targets with Learned Control Policies. IEEE Robotics and Automation Letters, doi: 10.1109/LRA.2023.3271508.
- Bakker, S.; Knoedler, L.; Spahn, M.; Böhmer, W. and Alonso-Mora J. (2023, MRS). Multi-Robot Local Motion Planning Using Dynamic Optimization Fabrics.. Proceedings to the 4th IEEE International Symposium on Multi-Robot and Multi-Agent Systems.
- Weltevrede, M.; Spaan, M. T. J., and Böhmer, W. (2023, EWRL). The Role of Diverse Replay for Generalisation in Reinforcement Learning. The 16th European Workshop on Reinforcement Learning.
- Zanger, M. A.; Böhmer, W., and Spaan M. T. J. (2023, EWRL). Diverse Projection Ensembles for Distributional Reinforcement Learning. The 16th European Workshop on Reinforcement Learning.
- Oren, Y.; Spaan, M. T. J., and Böhmer, W. (2023, EWRL). E-MCTS: Deep Exploration in Model-Based Reinforcement Learning by Planning with Epistemic Uncertainty. The 16th European Workshop on Reinforcement Learning.
2022
2021
- Peng, B., Rashid, T., Schröder de Witt, C.A., Kamienny, P.-A., Torr, P.H.S., Böhmer, W., Whiteson, S. (2021, NeurIPS). FACMAC: Factored Multi-Agent Centralised Policy Gradients. Advances in Neural Information Processing Systems.
- Gupta, T., Mahajan, A., Peng, B., Böhmer, W., and Whiteson, S. (2021, ICML). UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning. Proceedings of the International Conference on Machine Learning.
- Iqbal, S., Schröder de Witt, C., Peng, B., Böhmer, W., Whiteson, S., Sha, F. (2021, ICML). Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning. Proceedings of the International Conference on Machine Learning.
- Igl, M., Farquhar, G., Luketina, J., Böhmer, W., and Whiteson, S. (2021, ICLR). Transient Nonstationarity and Generalisation in Deep Reinforcement Learning. Proceedings of the International Conference on Learning Representations.
- Kurin, V., Igl, M., Rocktäschel, T., Böhmer, W., and Whiteson, S. (2021, ICLR). My Body is a Cage: the Role of Morphology in Graph-based Incompatible Control. Proceedings of the International Conference on Learning Representations.
- Pierotti, J., Kronmuüller, M., Alonso-Mora, J., van Essen, T., Böhmer, W. (2021). Reinforcement Learning for the Knapsack Problem. In Optimization and Data Science: Trends and Applications. AIRO Springer Series, vol 6.
2020
- Böhmer, W., Kurin, V., and Whiteson, S. (2020, ICML). Deep Coordination Graphs. Proceedings of the International Conference on Machine Learning.
- Igl, M., Gambardella, A., Nardelli, N., Siddharth, N., Böhmer, W., and Whiteson, S. (2020a, UAI). Multitask Soft Option Learning. Proceedings of the Conference on Uncertainty in Artificial Intelligence.
- Zhang, S., Böhmer, W., and Whiteson, S. (2020, AAMAS). Deep Residual Reinforcement Learning. Proceedings of the Nineteenth International Joint Conference on Autonomous Agents and Multi-Agent Systems (Best Paper Award).
- Rashid, T., Peng, B., Böhmer, W., and Whiteson, S. (2020, ICLR). Optimistic Exploration with Pessimistic Initialisation. Proceedings of the International Conference on Learning Representations.
- Igl, M., Böhmer, W., Whiteson, S. (2020b). ITER: Iterated Relearning for Improved Generalization in Reinforcement Learning. ICLR 2020 workshop Beyond "Tabula Rasa" in RL.
- Kamienny, P-A., Behbahani, F., Arulkumaran, K., Böhmer, W., Whiteson, S. (2020). Privileged Information Dropout in Reinforcement Learning. ICLR 2020 workshop Beyond "Tabula Rasa" in RL.
2019
- Schröder de Witt, C.A., Förster, J.N., Farquhar, G., Torr, P.H.S., Böhmer, W., and Whiteson, S. (2019, NeurIPS). Multi-Agent Common Knowledge Reinforcement Learning. Advances in Neural Information Processing Systems 32:9927-9939.
- Zhang, S., Böhmer, W., and Whiteson, S. (2019a, NeurIPS). Generalized Off-Policy Actor-Critic. Advances in Neural Information Processing Systems 2019.
- Han, D., Böhmer, W., Wooldridge, M., and Rodgers, A. (2019a, PRICAI). Multi-Agent Hierarchical Reinforcement Learning with Dynamic Termination. PRICAI 2019: Trends in Artificial Intelligence, part II, 80-92.
- Böhmer, W., Rashid, T., and Whiteson, S. (2019). Exploration with Unreliable Intrinsic Reward in Multi-Agent Reinforcement Learning. ICML Workshop on Exploration in Reinforcement Learning.
- Rashid, T., Böhmer, W., Peng, B., and Whiteson, S. (2019). Optimistic Exploration with Pessimistic Initialisation. ICML Workshop on Exploration in Reinforcement Learning.
- Zhang, S., Böhmer, W., and Whiteson, S. (2019b). Generalized Off-Policy Actor-Critic. ICML Workshop on Real-World Sequential Decision Making.
- Zhang, S., Böhmer, W., and Whiteson, S. (2019c). Deep Residual Reinforcement Learning. ICML Workshop on Real-World Sequential Decision Making.
- He, J., Igl, M., Smith, M., Böhmer, W., and Whiteson, S. (2019). Soft Option Transfer. NeurIPS 2019 Workshop on Learning Transferable Skills.
- Han, D., Böhmer, W., Wooldridge, M., and Rodgers, A. (2019b). Multi-Agent Hierarchical Reinforcement Learning with Dynamic Termination. Extended Abstract at AAMAS 2019.
2018
Igl, M., Böhmer, W., Gambardella, A., Nardelli, N., Siddharth, N., and Whiteson, S. (2018). Inference and Distillation for Option Learning. NeurIPS 2018 Workshop on Infer to Control.
2017
2016
- Guo, R., Böhmer, W., Hebart, M., Chien, S., Sommer, T., Obermayer, K., and Gläscher, J. (2016). Interaction of Instrumental and Goal-directed Learning Modulates Prediction Error Representations in the Ventral Striatum. Journal of Neuroscience, 36:12650-12660.
- Böhmer, W., Guo, R., and Obermayer, K. (2016). Non-deterministic Policy Improvement Stabilizes Approximate Reinforcement Learning. 13th European Workshop on Reinforcement Learning.
2015
- Böhmer, W., Springenberg, J.T., Boedecker, J., Riedmiller, M., and Obermayer, K. (2015a). Autonomous Learning of State Representations for Control: an emerging field aims to autonomously learnstate representations for reinforcement learning agents from their real-world sensor observations. KI - Künstliche Intelligenz 29(4): 353-362.
- Böhmer, W., and Obermayer K. (2015b, ECML). Regression with Linear Factored Functions. Proceedings to ECML/PKKD 2015 in Machine Learning and Knowledge Discovery in Databases, Volume 9284 of Lecture Notes in Computer Science, pp 119-134.
2014
- Tobia, M., Guo, R., Schwarze, U., Böhmer, W., Gläscher, J., Finckh, B., Marschner, A., Büchel, C., Obermayer, K., and Sommer, T. (2014). Neural Systems for Choice and Valuation with Counterfactual Learning Signals. Neuroimage 89:57-69.
2013
- Böhmer, W., Grünewälder, S., Shen, Y., Musial, M., and Obermayer, K. (2013a). Construction of Approximation Spaces for Reinforcement Learning. Journal of Machine Learning Research, 14:2067-2118.
- Houillon, A., Lorenz, R., Böhmer, W., Rapp, M., Heinz, A., Gallinat, J., and Obermayer, K. (2013). The Effect of Novelty on Reinforcement Learning. Progress in brain research 202:415-439.
- Böhmer, W., and Obermayer, K. (2013b). Towards Structural Generalization: Factored Approximate Planning. Workshop on Autonomous Learning at the International Conference on Robotics and Automation (ICRA 2013).
2012
2011
- Böhmer, W., Grünewälder, S., Nickisch, H., and Obermayer, K. (2011, ECML). Regularized Sparse Kernel Slow Feature Analysis. Machine Learning and Knowledge Discovery in Databases, Part I. Springer-Verlag Berlin Heidelberg, 235-248.