Description
Reinforcement Learning is the sub-field of AI that deals with how an software agent learns optimal decisions from data and by exploration. Our focus is on algorithm development and theory for advancing reinforcement learning to healthcare and social science. In particular, we focus on:
- Constrained exploration, e.g., in terms of fairness, safety
- Reinforcement learning from logged data and off-policy methods
- Economic and resource efficient reinforcement learning.
Latest publications
|
Intelligent Processing of Data Streams on the Edge Using Reinforcement Learning
In IEEE ICC 2023 Workshop on Scalable and Trustworthy AI for 6G Wireless Networks (6GSTRAIN), 2023 |
|||||||||
|
Comparing NARS and Reinforcement Learning: An Analysis of ONA and Q-Learning Algorithms
In International Conference on Artificial General Intelligence, 2023 |
|||||||||
|
Explaining Black Box Reinforcement Learning Agents Through Counterfactual Policies
In Advances in Intelligent Data Analysis XXI: 21st International Symposium on Intelligent Data Analysis, IDA 2023, Louvain-la-Neuve, Belgium, April 12–14, 2023, Proceedings, 2023 |
|||||||||
|
Policy Evaluation with Delayed, Aggregated Anonymous Feedback
In International Conference on Discovery Science, 2022 |
|||||||||
|
EpidRLearn: Learning Intervention Strategies for Epidemics with Reinforcement Learning
In Artificial Intelligence in Medicine, 2022 |
Related Projects
People
Sindri Magnússon, Associate Professor
distributed optimization, reinforcement learning, federated learning, IoT/CPS
Guilherme Dinis Chaliane Jr
learning dynamic multi-agent environments (Spotify)
Jonathan Piller
dynamic complex digital networks (Spotify)
Ali Beikmohammadi
efficient federated learning in complex networks
Shubham Vaishnav
reinforcement learning, federated learning, fog and edge networks optimization
Mohsen Amiri
reinforcement learning, federated learning, distributed optimization