Interactive Machine Learning

Keywords: Interactive learning & Decision making, Reinforcement learning, Multi-agent learning, Social signal processing, Active learning

Machine learning is getting more and more pervasive in our society. However, while much of machine learning assumes that the learner interacts with a static bag of data, in many of the applications this assumption does not hold. That is in many cases, an intelligent learning system will need to deal with: the long term effects of its predictions/actions; active acquisition of data; data coming from human behavior; changes in the environment, e.g., do to the presence of other learning systems. Interactive machine learning focuses on such challenges. 

Related Projects:

A video that shows
an intersection learning about the influence its past actions have on predicting and anticipating the future, about Explanation, about Multirobot coordination

Related tracks: ST, DST 

Related courses: 




Related Key publications:

  • M. Suau, E. Congeduti, R.A.N. Starre, A. Czechowski, F.A. Oliehoek, Influence-Based Abstraction in Deep Reinforcement Learning, Adaptive and Learning Agents Workshop at AAMAS 2019, Montreal
  • Sammie Katt, Frans A. Oliehoek, and Christopher Amato. Bayesian Reinforcement Learning in Factored POMDPs. In Proceedings of the Eighteenth International Conference on Autonomous Agents and Multiagent Systems (AAMAS), May 2019.
  • Frans A. Oliehoek, Rahul Savani, Jose Gallego-Posada, Elise van der Pol, and Roderich Gross. Beyond Local Nash Equilibria for Adversarial Networks. In Proceedings of the 27th Annual Machine Learning Conference of Belgium and the Netherlands (Benelearn), November 2018.
  • Frans A. Oliehoek. Interactive Learning and Decision Making: Foundations, Insights & Challenges. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI), pp. 5703–5708, July 2018.
  • Oertel, C., Cummins, F., Edlund, J., Wagner, P., & Campbell, N. (2013). D64: A corpus of richly recorded conversational interaction. Journal on Multimodal User Interfaces7(1-2), 19-28
  • Oertel, C., Wlodarczak, M., Tarasov, A., Campbell, N., & Wagner, P. (2012). Context cues for classification of competitive and collaborative overlaps.