In this presentation, Dr. Jonathan Dodge presents AiCommentator: A Multimodal Conversational Agent for Embedded Visualization in Football Viewing, by Andrews et al. In it, the authors demonstrate a method to do the necessary domain modeling, computer vision,...
In this presentation, Dr. Jonathan Dodge presents Human-level play in the game of Diplomacy by combining language models with strategic reasoning, by Bakhtin et al. In it, the authors work on a domain in which both planning and communication with other players are...
In this presentation, Dr. Jonathan Dodge presents his own work How Do People Rank Multiple Mutant Agents?. In it, we work on the MNK-games domain, introducing an agent and explanations, as well as a task for evaluating explanations (Ranking Task) and an operator for...
In this presentation, Dr. Jonathan Dodge presents SenseMate: An Accessible and Beginner-Friendly Human-AI Platform for Qualitative Data Analysis, by Overney et al. In it, the authors demonstrate UI to assist with human-AI collaboration for qualitative coding....
In this presentation, Dr. Jonathan Dodge presents Mastering the game of Stratego with model-free multiagent reinforcement learning, by Perolat et al. In it, the authors dispose of the Monte Carlo Tree Search (MCTS) systems of previous solutions, opting instead for a...