Automated Adaptation and Assessment in Serious Games: A Portable Tool for Supporting Learning

Abstract

Abstract. We introduce the Adaptation and Assessment (TwoA) component, an open-source tool for serious games, capable of adjusting game difficulty to player skill level. Technically, TwoA is compliant with the RAGE (Horizon 2020) game component architecture, which offers seamless portability to a variety of popular game development platforms. Conceptually, TwoA uses a modified version of the Computer Adaptive Practice algorithm. Our version offers two improvements over the original algorithm. First, the TwoA improves balancing of player's motivation and game challenge. Second, TwoA reduces the selection bias that may arise for items of similar difficulty by adopting a fuzzy selection rule. These improvements are validated using multi-agent simulations.

Portability of Serious Game Software Components

“…Among many RSCAA-compliant components currently available in the gamecomponents.eu portfolio, we will use the TwoA (Adaptation + Assessment) component [16], which uses a fuzzy-logic based algorithm for the real-time adaptation of task difficulty to user skill. The TwoA component assumes that there are multiple tasks of varying difficulty levels, which ideally can be controlled parametrically.…”

“…Through continued re-iteration of task difficulty and player's expertise level, it guides the player along the optimal learning curve. A detailed description of the adaptation mechanism is given in [16]. The C# implementation of the TwoA component has been extensively described elsewhere [6].…”

“…During porting the TwoA core functionality, issues arose with the SimpleRNG class as it used unsigned integers, which are not present in Java [16]. The common solution is to use bigger signed integers (so 32-bit unsigned integers are stored in 64-bit signed integers) [27].…”

“…The functioning of the ported component versions was tested by using the C# implementations as a reference. For TwoA, extensive validations of the C# version of the algorithm integrated in the TileZero game have been reported elsewhere, both using empirical performance data [16] and using machine-against-machine simulations [6]. A similar range of testing matches could then be simulated for the TypeScript/JavaScript and Java implementations by sampling from the performance data (match duration and outcome) produced by the C# simulation.…”

Set-theoretical and Combinatorial Instruments for Problem Space Analysis in Adaptive Serious Games

“…The section offers a short overview of the Computerized Adaptive Practice (CAP) algorithm. A more detailed discussion is available in [2,26]. CAP assumes that the game contains a set of playable single-player problems.…”