Alessandro Allievi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Alessandro Allievi has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
Felix Schmitt
1 shared publicationHolger Banzhaf
1 shared publication- Jarrett Holtz
Robert Bosch LLC., Budapest, Hungary
1 shared publication - Laszlo Szoke
Budapest University of Technology and Economics
1 shared publication Peter Stone
1 shared publication- Shahaf S. Shperberg
Faculty of Computer and Information Science, Ben-Gurion University of the Negev, Be’er Sheva, Israel
1 shared publication
Latest Publications
- 10 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (6) , 5174-5181
Adaptive Curriculum Learning With Successor Features for Imbalanced Compositional Reward Functions
This work addresses the challenge of reinforcement learning with reward functions that feature highly imbalanced components in terms of importance and scale. Reinforcement learning algorithms generally struggle to handle such imbalanced reward functions effectively. Consequently, they often converge to suboptimal policies that favor only the dominant reward component. For example, agents might adopt passive strategies, avoiding any action to evade potentially unsafe outcomes entirely. To mitigate the adverse effects of imbalanced reward functions, we introduce a curriculum learning approach based on the successor features representation. This novel approach enables our learning system to acquire policies that take into account all reward components, allowing for a more balanced and versatile decision-making process.
- 10 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (6) , 5174-5181
Adaptive Curriculum Learning With Successor Features for Imbalanced Compositional Reward Functions
This work addresses the challenge of reinforcement learning with reward functions that feature highly imbalanced components in terms of importance and scale. Reinforcement learning algorithms generally struggle to handle such imbalanced reward functions effectively. Consequently, they often converge to suboptimal policies that favor only the dominant reward component. For example, agents might adopt passive strategies, avoiding any action to evade potentially unsafe outcomes entirely. To mitigate the adverse effects of imbalanced reward functions, we introduce a curriculum learning approach based on the successor features representation. This novel approach enables our learning system to acquire policies that take into account all reward components, allowing for a more balanced and versatile decision-making process.
- Open Access
- 13 December 2022
- Published by Elsevier in Artificial Intelligence
- Vol. 316
Reward (Mis)design for autonomous driving
- 13 December 2022
- Published by Elsevier in Artificial Intelligence
- Vol. 316
Open AccessReward (Mis)design for autonomous driving