ColabTrails

Embodying intelligent behavior in social context

Abstract

Research has found that working in pairs or small groups can have beneficial effects on learning and development, particularly in early years and primary education (Benford et al., 2000). Although collaboration is very important during these early years it is implemented in a very minimal way at primary schools. In order to design a game which improves the collaboration between children from 6 to 8 years old, the existing game Colored Trails (Gal, Grosz, Kraus, Pfeffer & Shieber, 2005) was evaluated. From this evaluation, a new game, ColabTrails, was created which shares some mechanics with the Colored Trails game. The game aimed to encourage the players to collaborate by trading different colored tokens with each other to move across the board and finish earlier than the computer.

For the computer to sense and perform a smart or stupid move a learning algorithm needed to be implemented within the computer. Reinforcement learning was chosen for the concept. To be even more specific, the final prototype contains Q-learning. This algorithm simplifies the analysis and approximates the optimal action-value (Sutton & Barto, 1998). The agent will follow the optimal action-values for each movement to reach the final goal.

Reinforcement learning has proven to be a good tool to create a playful experience, and thus suitable for the social context and embodying intelligent behavior. During the user-deployment study, the prototype was perceived as too easy, several future work and improvements are suggested to keep the game interesting and to encourage the players to have a more elaborate collaboration. The algorithm can be applied better, in a way that the interaction between the two players will be led by the computer. To conclude the research of ColabTrails, we can say that we created a fun and interesting system steering children to collaborate, but not capable of letting the children realize the effects of this collaboration.

Responsibilities

Concept development

User interaction design

User interface

Implementation reinforcement learning

User deployment

Analyzing user experience

Low-fi prototype for user deployment

Low-fi prototype for user deployment

Envisioned interaction ColabTrails: before collaboration

Envisioned interaction ColabTrails: after collaboration

User & Society

Throughout the whole project my project group and I tried to focus on the collaboration between players through the use of an intelligent system. If look back on it, the game has evolved in such way that we just missed the point. Players are more focused on achieving their goal instead of collaborating to stay ahead of the computer. I think our intention was really good and relevant, but this is something to take in account next time.

I believe that by creating a human-computer interaction through the use of Embodied Social Technology a better connecting, smooth and desired interaction for both ends can be created. Humans will create more sympathy for the computer, which means that the interaction will be less overwhelming and more understandable. In addition, I believe that Embodied Social Technology can be a great solution to support or stimulate human-human interaction. Whether it involves a social problem between multiple people or can support a social handicap of someone.

Technology & Realisation

As a designer I want to focus on implicit interaction and how humans can fine-tune their desires within this type of interaction. By following the course Embodying Intelligent Behavior in Social Context I got more insights in the possibilities, sorts of intelligent algorithms and human-computer interactions. Something I consider as really valuable, because now I can see lots of possibilities in an early stage of my design process.

Because I already did a project that involved SVM learning, I preferred this time another type of machine learning. During the project I created the Processing-file which contained Reinforcement Learning (Q-learning) and therefore fully get to know the advantages and disadvantages of it.

Creativity & Aesthetics

In an early stage of our ideation phase, we decided as a group to focus stimulating collaborations between children in the form of a game. After some literature research we found the existing game Colored Trails and based our game on it. In order to fully define our game we decided to design our game while playing. This was really helpful, since we were able to pause the game to evaluate our actions. However, because we were not the target group we decided to simplify the rules and during the user deployment study the game was found to easy. Therefore, it was probably better to involve our target group in the ideation phase, so they could have an influence on our creativity.

References

Benford, S., Bederson, B. B., Ã…kesson, K. P., Bayon, V., Druin, A., Hansson, P., ... & Simsarian, K. T. (2000, April). Designing storytelling technologies to encouraging collaboration between young children. In Proceedings of the SIGCHI conference on Human Factors in Computing Systems (pp. 556-563). ACM.

Gal, Y. A., Grosz, B. J., Kraus, S., Pfeffer, A., & Shieber, S. (2005, July). Colored trails: a formalism for investigating decision-making in strategic environments. In Proceedings of the 2005 IJCAI workshop on reasoning, representation, and learning in computer games (pp. 25-30).

Sutton, R. S., & Barto, A. G. (1998). Reinforcement learning an introduction. Cambridge, Mass.: MIT Press.

© 2020 Jesper van Bentum