Boris Belousov

Research Interests
Robot Learning, Optimal Control, Decision Theory, MaxEnt Methods, Active Perception, Tactile Sensing
Affiliations
1. German Research Center for AI (DFKI), Research Department: SAIROL
2. TU Darmstadt, Intelligent Autonomous Systems, Computer Science Department
Contact
boris.belousov@dfki.de
Room 2.1.16, Building S4|14, DFKI, SAIROL, Mornewegstraße 30, 64293 Darmstadt
Boris Belousov has graduated but remains adjunct to IAS while being a Senior Researcher at the German Research Center for AI (DFKI), Research Department: Systems AI for Robot Learning. He holds a MSc degree in Electrical Engineering from FAU Erlangen-Nürnberg with a major in Communications and Multimedia Engineering and a BSc degree in Applied Mathematics and Physics from Moscow Institute of Physics and Technology with a specialization in Electrical Engineering and Cybernetics.
Supervision
Boris Belousov has supervised 14 M.Sc. theses, 4 B.Sc. theses, 20 IP projects. See Supervised Theses.
Teaching
Reinforcement Learning WS'18
Statistical Machine Learning SS'18
Robot Learning IP WS'17
Reviewing
JMLR, NeurIPS, ICML, AAAI, ICLR, CORL, ICRA, IROS, AURO, RA-L, TR-O, R:SS
Boris Belousov is interested in optimal control, information theory, robotics, and reinforcement learning. To realize the vision of intelligent systems of the future—that autonomously set and accomplish goals, learn from experience and adapt to changing conditions—Boris develops methods that are firmly grounded in Bayesian decision theory. He has worked on maximum entropy reinforcement learning, risk-sensitive policy search, active learning, distributionally robust trajectory optimization, curriculum learning, domain randomization, visuotactile manipulation.
Publications
Systems AI for Robot Learning
-
- Vincent, T.; Belousov, B.; D'Eramo, C.; Peters J. (2023). Iterated Deep Q-Network: Efficient Learning of Bellman Iterations for Deep Reinforcement Learning, European Workshop on Reinforcement Learning (EWRL).
-
- Lutter, M.; Belousov, B.; Mannor, S.; Fox, D.; Garg, A.; Peters, J. (2023). Continuous-Time Fitted Value Iteration for Robust Policies, IEEE Transaction on Pattern Analysis and Machine Intelligence (PAMI).
-
- Siebenborn, M.; Belousov, B.; Huang, J.; Peters, J. (2022). How Crucial is Transformer in Decision Transformer?, Foundation Models for Decision Making Workshop at Neural Information Processing Systems.
-
- Galljamov, R.; Zhao, G.; Belousov, B.; Seyfarth, A.; Peters, J. (2022). Improving Sample Efficiency of Deep Reinforcement Learning for Bipedal Walking, 2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids).
-
- Belousov, B.; Abdulsamad H.; Klink, P.; Parisi, S.; Peters, J. (2021). Reinforcement Learning Algorithms: Analysis and Applications, Studies in Computational Intelligence, Springer International Publishing.
Reinforcement Learning and Tactile Manipulation for Robotic Assembly
-
- Liu, Y.; Belousov, B.; Funk, N.; Chalvatzaki, G.; Peters, J.; Tessman, O. (2023). Auto(mated)nomous Assembly, International Conference on Trends on Construction in the Post-Digital Era, pp.167-181, Springer, Cham.
-
- Belousov, B.; Wibranek, B.; Schneider, J.; Schneider, T.; Chalvatzaki, G.; Peters, J.; Tessmann, O. (2022). Robotic Architectural Assembly with Tactile Skills: Simulation and Optimization, Automation in Construction, 133, pp.104006.
-
- Funk, N.; Chalvatzaki, G.; Belousov, B.; Peters, J. (2021). Learn2Assemble with Structured Representations and Search for Robotic Architectural Construction, Conference on Robot Learning (CoRL).
-
- Wibranek, B.; Liu, Y.; Funk, N.; Belousov, B.; Peters, J.; Tessmann, O. (2021). Reinforcement Learning for Sequential Assembly of SL-Blocks: Self-Interlocking Combinatorial Design Based on Machine Learning, Proceedings of the 39th eCAADe Conference.
-
- Belousov, B.; Sadybakasov, A.; Wibranek, B.; Veiga, F.; Tessmann, O.; Peters, J. (2019). Building a Library of Tactile Skills Based on FingerVision, Proceedings of the 2019 IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids).
-
- Wibranek, B.; Belousov, B.; Sadybakasov, A.; Peters, J.; Tessmann, O. (2019). Interactive Structure: Robotic Repositioning of Vertical Elements in Man-Machine Collaborative Assembly through Vision-Based Tactile Sensing, Proceedings of the 37th eCAADe and 23rd SIGraDi Conference.
-
- Wibranek, B.; Belousov, B.; Sadybakasov, A.; Tessmann, O. (2019). Interactive Assemblies: Man-Machine Collaboration through Building Components for As-Built Digital Models, Computer-Aided Architectural Design Futures (CAAD Futures).
Maximum Entropy Reinforcement Learning and Stochastic Optimal Control
-
- Abdulsamad, H.; Dorau, T.; Belousov, B.; Zhu, J.-J; Peters, J. (2021). Distributionally Robust Trajectory Optimization Under Uncertain Dynamics via Relative Entropy Trust-Regions, arXiv.
-
- Klink, P.; Abdulsamad, H.; Belousov, B.; D'Eramo, C.; Peters, J.; Pajarinen, J. (2021). A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning, Journal of Machine Learning Research (JMLR).
-
- Eilers, C.; Eschmann, J.; Menzenbach, R.; Belousov, B.; Muratore, F.; Peters, J. (2020). Underactuated Waypoint Trajectory Optimization for Light Painting Photography, Proceedings of the IEEE International Conference on Robotics and Automation (ICRA).
-
- Lutter, M.; Belousov, B.; Listmann, K.; Clever, D.; Peters, J. (2019). HJB Optimal Feedback Control with Deep Differential Value Functions and Action Constraints, Conference on Robot Learning (CoRL).
-
- Belousov, B.; Peters, J. (2019). Entropic Regularization of Markov Decision Processes, Entropy, 21, 7, MDPI.
-
- Klink, P.; Abdulsamad, H.; Belousov, B.; Peters, J. (2019). Self-Paced Contextual Reinforcement Learning, Proceedings of the 3rd Conference on Robot Learning (CoRL).
-
- Nass, D.; Belousov, B.; Peters, J. (2019). Entropic Risk Measure in Policy Search, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
-
- Belousov, B.; Peters, J. (2018). Mean Squared Advantage Minimization as a Consequence of Entropic Policy Improvement Regularization, European Workshops on Reinforcement Learning (EWRL).
-
- Belousov, B.; Peters, J. (2017). f-Divergence Constrained Policy Improvement, arXiv.
-
- Belousov, B.; Neumann, G.; Rothkopf, C.; Peters, J. (2016). Catching Heuristics Are Optimal Control Policies, Advances in Neural Information Processing Systems (NIPS / NeurIPS).
Information-Theoretic Active Exploration
-
- Schneider, T.; Belousov, B.; Chalvatzaki, G.; Romeres, D.; Jha, D.K.; Peters, J. (2022). Active Exploration for Robotic Manipulation, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
-
- Schneider, T.; Belousov, B.; Abdulsamad, H.; Peters, J. (2022). Active Inference for Robotic Manipulation, 5th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM).
-
- Muratore, F.; Gruner, T.; Wiese, F.; Belousov, B.; Gienger, M.; Peters, J. (2021). Neural Posterior Domain Randomization, Conference on Robot Learning (CoRL).
-
- Belousov, B.; Abdulsamad, H.; Schultheis, M.; Peters, J. (2019). Belief Space Model Predictive Control for Approximately Optimal System Identification, 4th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM).
-
- Schultheis, M.; Belousov, B.; Abdulsamad, H.; Peters, J. (2019). Receding Horizon Curiosity, Proceedings of the 3rd Conference on Robot Learning (CoRL).