Flow in Artificial Intelligence
The psychological condition of flow has been linked to optimizing cognitive performance in humans (Csikszentmihalyi, 1990). People experiencing the condition of flow appear to be fully engaged in their task, and their cognitive faculties and attention are fully focused on the task. In order for this to happen, there has to be a match between the task complexity and the individual’s abilities. Tasks that are too simple or too complex for the individual cause other psychological states such as boredom or anxiety. Reaching the condition of flow has been linked to a number of benefits, including higher productivity and happiness. Hence, flow appears to optimize the application of cognitive abilities in humans. Thus, it is of interest to model flow mathematically as well as to consider whether giving artificial cognitive agents an ability to sense flow and the desire to maximize flow can optimize their performance too.
We first defined the degree of flow as the quality of the match between the agent’s cognitive skills and the cognitive complexity of its current task. In a hierarchy of increasingly more complex and rewarding tasks, taking on the task of a matching complexity allows the agent to maximize its performance. It also consequently maximizes the degree of flow the agent will experience. We took advantage of this connection and make our agents explicitly aware of the degree of flow they are experiencing. Maximizing the readings from such a “flow meter” improves the agent’s ability to explore the environment and find problems of matching complexity. Thus, maximizing the degree of flow becomes a guide to maximizing the agent’s performance in the environment. We implemented these ideas by extending the standard value iteration learning method with planning and real-time operation and empirically demonstrate that flow-maximizing agents tend to collect more reward from the environment
We are extending our flow meter model to richer environments such as the progressively more difficult dungeons the player traverses in the video game of Angband. We are also investigating formation of a flow meter as an evolutionary adaptation.
- Vadim Bulitko and David Thue. 2015. A Call for Flow Modeling in Interactive Storytelling. Advances in Cognitive Systems, Cognitive Systems Foundation, volume 4, pages 25–34.
- Thórey Maríusdóttir and Vadim Bulitko and Matthew Brown. 2015. Maximizing Flow as a Metacontrol in Angband. In Proceedings of the Eleventh AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE), pages 149-155. Stanford, CA.
- Vadim Bulitko and David Thue. 2015. A Call for Flow Modeling in Interactive Storytelling. In Proceedings of The Third Annual Conference on Advances in Cognitive Systems (ACS). Pages 10. Atlanta, GA.
- Vadim Bulitko. 2014. Flow for Meta Control. The seventh conference on Artificial General Intelligence, published on-line. Pages 10. Quebec City, Quebec. arXiv: 1407.4709 [cs.AI].
- Vadim Bulitko and Matthew Brown. 2012. Flow Maximization as a Guide to Optimizing Performance: A Computational Model. Advances in Cognitive Systems, Cognitive Systems Foundation, volume 2, pages 239-256.
- A Call for Flow Modeling in Interactive Storytelling. CMN Workshop. Atlanta, Georgia. May 28, 2015.
- Computational Models of Flow. Invited talk at CogSem, Department of Psychology. University of Alberta. Edmonton, Alberta. January 16, 2015. Co-authored with T. Mariusdottir.
- Flow of Interactive Storytelling. AI Seminar. University of Alberta. Edmonton, Alberta. November 28, 2014.
- From Human Writers to AI Experience Managers. Liquid Narrative Group. North Carolina State University. Raleigh, North Carolina. October 8, 2014.
- Managing Interactive Experience with Artificial Intelligence. Invited talk for Computational Media and Design program. University of Calgary. Alberta. September 29, 2014.
- Interactive Storytelling for Fun and Training. Invited talk at CogSem, Department of Psychology. University of Alberta. Edmonton, Alberta. September 12, 2014.
- Flow for Meta Control. AGI-2014 Special Session on AGI and Cognitive Science, Quebec City, QC. August 4, 2014.
- Flow and Reinforcement Learning. RLAI Group. University of Alberta. July 22, 2013.
- Flow Maximization for Optimizing Performance. First Annual Conference on Advances in Cognitive Science. Palo Alto, California. December 8, 2012.