During my internship at La Forge, Ubisoft Monreal I implemented reinforcement learning agents using Unity3D Machine Learning AI Agents. My focus was on using reinforcement learning techniquest for complex physics based navigation. During my internship I had the opportunity to explore different ideas such as visualizing value functinos as design aids, or using hierarchical reinforcement learning techniques to increase sample efficieny. What I am currently trying to do is implementing different learning enviroments in Unity3D and streamlining the experience for others to use the framework by making tutorials.
Failure is integral to playing videogames, we do not have a precise terminology for discussing different categories of failure. This is a problem because certain failures are critical to the design intent of the game, and, as such, are desirable, whereas other failures detract from the play experience and are meant to be avoided. In this paper, we taxonomize several classes of failure in the player's experience, offering a diagnostic tool that distinguishes in-loop failures from out-of-loop failures. By classifying both games and specific failure instances, the Taxonomy of Failure extends present vocabularies for: game designers making design choices, scholars critiquing the usability of games, educators teaching games, data analysts segmenting players, and game developers creating more adaptive games.
Most tutorials in video games do not consider the skill level of the player when deciding what information to present. This makes many tutorials either tedious for experienced players or not informative enough for players who are new to the given genre. With Talin, implemented as an asset in the Unity game engine, we make it possible to create a mastery model of an individual player's skill levels by operationalizing Dan Cook's skill atom theory. We propose that using this mastery model opens up a new design space when it comes to designing tutorials. We show an example tutorial implementation with Talin assembled using only graphical components provided by our framework, without the need of writing any code. The dynamic tutorial implementation results in the player receiving information only when they need it, whenever they need it. While the novice player is given all the information they need to learn the system, the expert player is not bogged down by tooltip pop-ups regarding mechanics they have already mastered.
Cargie is a robotics project that is made by combining Positional Tracking Cameras, Unity3D and Arduino. Prototyped to help of Etihad Airways automate their ground cargo operation, Cargie offers a scalable method of moving heavy and dangerous goods from Point A to Point B with ease. The cameras track Cargie's position, which is then mapped into a virtual representation of the area that is created in Unity3D. This structure allows Cargie to have a birds eye view of the whole space and enables pathfinding between arbitrary points. You can see Cargie in action here
Conciousness is a Virtual Reality game for HTC Vive made by Unity3D . The player paddles through an "endless" paddler, trying to outrun a dark monster. Unlike other endless runners there is an underlying story and the player can uncover bits and pieces by destroying the floating crystals. You can watch an ongoing play test here.
Play A to Start is a game that that helps people practice their musical insturments. Unlike other similar games however PA2S focuses on improvisation and creativity. Instead of offering a set song to play, the game offers a rythm and a combination of different notes and allows the player to practice their creativity given the constraints. The project is built using P5Js . The game was also featured in IMPACT Conference 2016.
- Xueer Zhu, AI Programmer on Assitive AI project
- Eri Hu, AI Programmer on Assitive AI project
- Hunter Lynch, User Reseracher on the SMES project
- Carl Erez, GUI Programmer on the SMES project
- Yuqing Yan, Designer on the SMES project
- Pengze Zheng, Aethetics of Failure project
- Katie Moses, on her Winter in June project