1. 9.3 Learning to Team-Based Navigation: A Review of Deep Reinforcement Learning Techniques for Multi-Agent Pathfinding
   • Authors: Jaehoon Chung, Jamil Fayyad, Younes Al Younes, Homayoun Najjaran
   • The authors of this paper are experts in the field and the topic is highly relevant in large-scale robotic applications. It provides a comprehensive review of DRL-based approaches which can have a far-reaching impact on MAPF research.
2. 9.0 Reinforcement Logic Rule Learning for Temporal Point Processes
   • Authors: Chao Yang, Lu Wang, Kun Gao, Shuang Li
   • This paper proposes a novel algorithm for optimization of explanatory temporal logic rule set. It provides a new perspective on the problem by integrating advanced optimization with reinforcement learning.
3. 8.8 Neural Conversation Models and How to Rein Them in: A Survey of Failures and Fixes
   • Authors: Fabian Galetzka, Anne Beyer, David Schlangen
   • This paper’s framework of how neural conversation model should be structured offers a pioneering perspective. The authors’ comprehensive study on the failures and fixes of the system is of high value to this field.
4. 8.5 Learning Control Policies for Variable Objectives from Offline Data
   • Authors: Marc Weber, Phillip Swazinna, Daniel Hein, Steffen Udluft, Volkmar Sterzing
   • The paper speaks about offline reinforcement learning method to control dynamic systems which can be impactful in this field.
5. 8.1 Towards a Causal Probabilistic Framework for Prediction, Action-Selection & Explanations for Robot Block-Stacking Tasks
   • Authors: Ricardo Cannizzaro, Jonathan Routley, Lars Kunze
   • This work proposes a new framework to combine physics simulation with a structural causal model. The contribution here could inspire future works in the domain of robotics and manipulation tasks.