Generating Educational Game Levels with Multistep Deep Convolutional Generative Adversarial Networks

Park, Kyungjin; Mott, Bradford W.; Min, Wookhee; Boyer, Kristy Elizabeth; Wiebe, Eric N.; Lester, James C.

doi:10.1109/cig.2019.8848085

Cited by 32 publications

(27 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Significant steps have been taken towards making blockbased programming environments adaptive [23], [24]; however, it is still difficult to find block-based programming environments that offer adaptive gameplay to fit individual learners' needs [25].…”

Section: B Block-based Programming Environmentsmentioning

confidence: 99%

First Steps Towards Automatically Defining the Difficulty of Maze-Based Programming Challenges

Kanellopoulou

Garaizar

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

Section: B Block-based Programming Environmentsmentioning

confidence: 99%

First Steps Towards Automatically Defining the Difficulty of Maze-Based Programming Challenges

Kanellopoulou

Garaizar

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The idea of using procedural tools to generate game scenes or entire levels is not new [1], [2], [3], [6], [7], [8]. These methods were used to generate indoor (e.g.…”

Section: Procedural Game Scenes Generationmentioning

confidence: 99%

“…One of the ways to reduce the burden of the level design is to automate the process of scene content creation with procedural and machine learning (ML) methods [1], [2], [3], [4], [5], [6], [7], [8]. Besides the terrain creation which can be achieved separately, we can consider the automatic content creation process as a series of steps.…”

Section: Introductionmentioning

confidence: 99%

HyperColor: A HyperNetwork Approach for Synthesizing Auto-colored 3D Models for Game Scenes Population

Kostiuk¹,

Stachura²,

Tadeja³

et al. 2021

Preprint

View full text Add to dashboard Cite

Designing a 3D game scene is a tedious task that often requires a substantial amount of work. Typically, this task involves synthesis, coloring, and placement of 3D models within the game scene. To lessen this workload, we can apply machine learning to automate some aspects of the game scene development. Earlier research has already tackled automated generation of the game scene background with machine learning. However, model auto-coloring remains an underexplored problem. The automatic coloring of a 3D model is a challenging task, especially when dealing with the digital representation of a colorful, multipart object. In such a case, we have to "understand" the object's composition and coloring scheme of each part. Existing single-stage methods have their own caveats such as the need for segmentation of the object or generating individual parts that have to be assembled together to yield the final model. We address these limitations by proposing a two-stage training approach to synthesize auto-colored 3D models. In the first stage, we obtain a 3D point cloud representing a 3D object, whilst in the second stage, we assign colors to points within such cloud. Next, by leveraging the so-called triangulation trick, we generate a 3D mesh in which the surfaces are colored based on interpolation of colored points representing vertices of a given mesh triangle. This approach allows us to generate a smooth coloring scheme. Experimental evaluation shows that our two-stage approach gives better results in terms of shape reconstruction and coloring when compared to traditional single-stage techniques.

show abstract

“…Edugame(educational game), very interesting to develop [10][11][12][13][14][15]. Because by playing educational games on any platform, they will indirectly learn something knowledge in the form of a game [11,13].…”

Section: Introductionmentioning

confidence: 99%

Development Finite State Machine Agent in Edugame "Hangug Word" Learning Media of Korea Hangul Letters

Nursobah

Andrea

Kurniawan

2021

mib

View full text Add to dashboard Cite

Development the edugame "Hangug Word", learning media of to Korean Hangul letters with game Agent Finite State Machine based on Android. The application used in making the game is Swish max4. In this game, a game agent character is given. In the game agent using the Finite State Machine (FSM) method, the Game Agent will notify the players if they answer incorrectly or correctly in the game. The Finite State Machine method of designing a control system that describes the working principle of the system using three things: state, event, action used in the game agent can provide action and reaction to players when the game is played. The results of making this edugame are .Apk and .Swf which can be run on an Android smartphone.

show abstract

Generating Educational Game Levels with Multistep Deep Convolutional Generative Adversarial Networks

Cited by 32 publications

References 22 publications

First Steps Towards Automatically Defining the Difficulty of Maze-Based Programming Challenges

First Steps Towards Automatically Defining the Difficulty of Maze-Based Programming Challenges

HyperColor: A HyperNetwork Approach for Synthesizing Auto-colored 3D Models for Game Scenes Population

Development Finite State Machine Agent in Edugame "Hangug Word" Learning Media of Korea Hangul Letters

Contact Info

Product

Resources

About