Alessandro Giacomo Bottero
Research Interests
Machine Learning, Robotics, Reinforcement Learning, Bayesian Optimization
Affiliations
- Bosch Centre for Artificial Intelligence
- TU Darmstadt, Intelligent Autonomous Systems, Computer Science Department
Contact Information
alessandro.bottero@robot-learning.de
+49-172-2106532
Robert Bosch GmbH, Robert-Bosch-Campus 1, 71272 Renningen
Alessandro Giacomo Bottero joined the Intelligent Autonomous Systems group in April 2021 as an external Ph.D. student in collaboration with the Bosch Center for Artificial Intelligence (BCAI). In his research, he focuses on safe exploration in reinforcement learning (RL), a key challenge to be able to apply RL solutions to real world problems.
Before joining IAS and BCAI, he worked as Software Consultant at TNG - Technology consulting, where he started working after completing a B.Sc. in physics at the University of Pavia and a M.Sc. in theoretical and mathematical physics at LMU and TU München. Please look at his complete Curriculum Vitae.
Publications
- Luis, C.E.; Bottero, A.G.; Vinogradska, J.; Berkenkamp, F.; Peters, J. (in press). Uncertainty Representations in State-Space Layers for Deep Reinforcement Learning under Partial Observability, Transactions on Machine Learning Research (TMLR).
- Luis, C.E.; Bottero, A.G.; Vinogradska, J.; Berkenkamp, F.; Peters, J. (2024). Value-Distributional Model-Based Reinforcement Learning, Journal of Machine Learning Research (JMLR), 25, 298, pp.1-42.
- Luis, C.; Bottero, A.G.; Vinogradska, J.; Berkenkamp, F.; Peters, J. (2023). Model-Based Uncertainty in Value Functions, Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS).
- Bottero, A.G.; Luis, C.E.; Vinogradska, J.; Berkenkamp, F.; Peters, J. (2022). Information-Theoretic Safe Exploration with Gaussian Processes, Advances in Neural Information Processing Systems (NIPS / NeurIPS).