1. 9.2 Deep Multi-Agent Reinforcement Learning for Decentralized Active Hypothesis Testing
   • Authors: Hadar Szostak, Kobi Cohen
   • The paper presents a novel approach using deep multi-agent reinforcement learning to the active hypothesis testing problem. It contains applications to real-world problems, and assistance is given to the scientific community with their open-source implementation. This can greatly influence the development and application of multi-agent systems.
2. 9.1 Deep-learning-powered data analysis in plankton ecology
   • Authors: Harshith Bachimanchi, Matthew I.M. Pinder, Chloé Robert, Pierre De Wit, Jonathan Havenhand, Alexandra Kinnby, Daniel Midtvedt, Erik Selander, Giovanni Volpe
   • Deep learning application to plankton ecology presents a significant advancement in the scientific community. The authors provide an in-depth analysis of deep learning methods in plankton data analysis and discuss possible future improvements. The addition of tutorials and code samples increases its potential influence.
3. 9.0 Deep Reinforcement Learning for Efficient and Fair Allocation of Health Care Resources
   • Authors: Yikuan Li, Chengsheng Mao, Kaixuan Huang, Hanyin Wang, Zheng Yu, Mengdi Wang, Yuan Luo
   • This paper addresses the crucial problem in healthcare, the allocation of scarce resources. It presents a deep reinforcement learning approach for efficient and fair allocation and enables improvements in patient outcomes and equitable distribution. This paper has a high potential influence because of its relevance for important practical problems.
4. 8.9 Quantitative and Qualitative Evaluation of Reinforcement Learning Policies for Autonomous Vehicles
   • Authors: Laura Ferrarotti, Massimiliano Luca, Gabriele Santin, Giorgio Previati, Gianpiero Mastinu, Elena Campi, Lorenzo Uccello, Antonino Albanese, Praveen Zalaya, Alessandro Roccasalva, Bruno Lepri
   • This paper discusses optimizing choices for autonomous vehicles (AVs) using reinforcement learning. The study involves both quality and quantity aspects. It has strong implications for the improvement of the future of transportation.
5. 8.8 Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization
   • Authors: Jack Foster, Alexandra Brintrup
   • The paper introduces a novel method for continual learning, that is lightweight and task label-free, converges quickly, and provides calibrated uncertainty for safer real-world deployment. It has wide implications for the deployment of long-term autonomous robotic agents.