So! There’s a newer version of Ropossum! The new version of Ropossum will feature a new [awesome] functionality for players and designers alike. (if you don’t know about Ropossum.. uh.. com’on, who don’t know about it?! take a look here and here.)
Peek view on the new version is the following screen shots (which I hope you may not understand :P) Ropossum V2.0 will feature two new agents and an improved user interface for easy realtime interaction with the system (for example and to keep you interested, generating levels is a massive 35 times faster than the previous version by one of the two new agents!). There’s a big step on the overall performance and efficiency of the system. A competition for Cut the Rope: Play Forever and Ropossum may took place in the near future, not sure though.
Interested? Please let me know by email if you want [firstname.lastname@example.org] or share your opinion down below in the comments.
Keep tuned! And as always.. great things are COMING! Ropossum V3.0 development has already begun with a new direction!
This was the seminar I did in Artificial Neural Networks (ANN) back in 2011 at F.I.T.E Damascus, Syria. I encountered the problem of generating game content based on players preferences. For this, I have discussed two papers in the seminar:
- Towards Automatic Personalized Content Generation for Platform Games. Noor Shaker, Georgios N. Yannakakis, Member, IEEE, and Julian Togelius, Member, IEEE
- Feature Analysis for Modeling Game Content Quality. Noor Shaker, Georgios N. Yannakakis, Member, IEEE, and Julian Togelius, Member, IEEE
It’s interesting to say that I have been supervised by Noor Shaker (one of the author of the two mentioned papers) for a new research project (back in 2011 and ongoing) which investigates generating content for more immersive experience games; Generating Adaptive Content for First-Person Shooter Games and further working with her for Utilising Visual Features as Indicators of Players Engagement in Super Mario Bros.
Very interesting stuff can be found for this domain in the published paper of the authors: Noor Shaker, Georgios N. Yannakakis and Julian Togelius.
The presentation and poster was part of my fourth year project in Information Technology Engineering, Artificial Intelligence Department, Damascus, Syria. This research study take games development concept to a new level, especially the so called First Person Shooter (FPS) Games. This study outline three basic models: FPS Game Level Design and Procedural Content Generation for FPS games, Preference Learning and Adaptive Content Generation. The framework has been integrated with CUBE opensource game engine. A conference paper has been published in UMAP 2013 which you can find in the publication section (with Noor Shaker, Mehdi Zonji, Ismaeel Abu Abdalla and Mhd Hasan Sarhan.) In this paper (abstract), we describe a methodology for capturing player experience while interacting with a game and we present a data-driven approach for modelling this interaction. We believe the best way to adapt games to a specific player is to use quantitative models of player experience derived from the in-game interaction. Therefore, we rely on crowd-sourced data collected about game context, players behaviour and players self-reports of different affective states. Based on this information, we construct estimators of player experience using neuroevolutionary preference learning. We present the experimental setup and the results obtained from a recent case study where accurate estimators were constructed based on information collected from players playing a first person shooter game. The framework presented is part of a bigger picture where the generated models are utilized to tailor content generation to particular player’s needs and playing characteristics. Authors are: Noor Shaker, Mohammad Shaker, Ismaeel Abuabdallah, Mehdi Zonjy, and Mhd Hasan Sarhan.
The poster we presented in the Extended Proceedings of the 2013 Conference on User Modeling, Adaptation and Persolization (UMAP 2013), 2013.
You can download the full project documentation [in Arabic – بالعربية] here.
This is the poster we presented in the Proceedings of Artificial Intelligence and Interactive Digital Entertainment (AIIDE 13), 2013. You can take a look at the papers in the publication section. You can also download the two papers from here and here. In these two paper we present Ropossum, an authoring tool for the generation and testing of levels of the physics-based game, Cut the Rope. Ropossum integrates many features: (1) automatic design of complete solvable content, (2) incorporation of designer’s input through the creation of complete or partial designs, (3) automatic check for playability and (4) optimization of a given design based on playability. The system includes a physics engine to simulate the game and an evolutionary framework to evolve content as well as an AI reasoning agent to check for playability. The system is optimised to allow on-line feedback and realtime interaction. The authors are Mohammad Shaker [Me] with Noor Shaker and Julian Togelius.