It is our great pleasure to welcome you to the 26th International Conference on Multimodal Interaction (ICMI 2024) in San Jose, Costa Rica. This is the first ICMI held in Latin America. ICMI is the premier international forum for human-centered multimodal interaction and social artificial intelligence (AI). Multimodal human-centered AI includes machine learning and computational techniques, such as representation learning, fusion, data and systems. The study of social interactions includes both human-human and human-machine interactions. A unique aspect of ICMI is its multidisciplinary nature which values both scientific discoveries and technical modeling of human interaction towards positive and societally beneficial applications. We are keen to showcase the recent advances in the field to the community and provide an inclusive forum to develop and exchange new ideas. To this end, a new initiative committee has been established to organize events for newcomers and facilitate inclusion. [...]@en

Interactive reinforcement learning provides a way for agents to learn to solve tasks from evaluative feedback provided by a human user. Previous research showed that humans give copious feedback early in training but very sparsely thereafter. In this paper, we investigate the potential of agent learning from trainers’ facial expressions via interpreting them as evaluative feedback. To do so, we implemented TAMER which is a popular interactive reinforcement learning method in a reinforcement-learning benchmark problem — Infinite Mario, and conducted the first large-scale study of TAMER involving 561 participants. With designed CNN-RNN model, our analysis shows that telling trainers to use facial expressions and competition can improve the accuracies for estimating positive and negative feedback using facial expressions. In addition, our results with a simulation experiment show that learning solely from predicted feedback based on facial expressions is possible and using strong/effective prediction models or a regression method, facial responses would significantly improve the performance of agents. Furthermore, our experiment supports previous studies demonstrating the importance of bi-directional feedback and competitive elements in the training interface. @en

Interactive reinforcement learning provides a way for agents to learn to solve tasks from evaluative feedback provided by a human user. Previous research showed that humans give copious feedback early in training but very sparsely thereafter. In this article, we investigate the potential of agent learning from trainers’ facial expressions via interpreting them as evaluative feedback. To do so, we implemented TAMER which is a popular interactive reinforcement learning method in a reinforcement-learning benchmark problem—Infinite Mario, and conducted the first large-scale study of TAMER involving 561 participants. With designed CNN–RNN model, our analysis shows that telling trainers to use facial expressions and competition can improve the accuracies for estimating positive and negative feedback using facial expressions. In addition, our results with a simulation experiment show that learning solely from predicted feedback based on facial expressions is possible and using strong/effective prediction models or a regression method, facial responses would significantly improve the performance of agents. Furthermore, our experiment supports previous studies demonstrating the importance of bi-directional feedback and competitive elements in the training interface.

@en