Using a Team of General AI Algorithms to Assist Game Design and Testing

Guerrero-Romero, Cristina; Lucas, Simon M.; Peŕez-Liebana, Diego

doi:10.1109/cig.2018.8490417

Cited by 22 publications

(11 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the authors of [26] stated, since the agent was a gameplaying agent, the agent was not required to find all of the bugs. Lastly, [27] introduced a team of agents with different purposes to test games. Nonetheless, all of these studies lack controlled experimentation.…”

Section: Related Researchmentioning

confidence: 99%

Automated Video Game Testing Using Synthetic and Humanlike Agents

2021

View full text Add to dashboard Cite

In this paper, we present a new methodology that employs tester agents to automate video game testing. We introduce two types of agents -synthetic and human-like-and two distinct approaches to create them. Our agents are derived from Reinforcement Learning (RL) and Monte Carlo Tree Search (MCTS) agents, but focus on finding defects. The synthetic agent uses test goals generated from game scenarios, and these goals are further modified to examine the effects of unintended game transitions. The human-like agent uses test goals extracted by our proposed multiple greedy-policy inverse reinforcement learning (MGP-IRL) algorithm from tester trajectories. MGP-IRL captures multiple policies executed by human testers. These testers' aims are finding defects while interacting with the game to break it, which is considerably different from game playing. We present interaction states to model such interactions. We use our agents to produce test sequences, run the game with these sequences, and check the game for each run with an automated test oracle. We analyze the proposed method in two parts: we compare the success of human-like and synthetic agents in bug finding, and we evaluate the similarity between humanlike agents and human testers. We collected 427 trajectories from human testers using the General Video Game Artificial Intelligence (GVG-AI) framework and created three games with 12 levels that contain 45 bugs. Our experiments reveal that human-like and synthetic agents compete with human testers' bug finding performances. Moreover, we show that MGP-IRL increases the human-likeness of agents while improving the bug finding performance.

show abstract

Section: Related Researchmentioning

confidence: 99%

Automated Video Game Testing Using Synthetic and Humanlike Agents

2021

View full text Add to dashboard Cite

show abstract

“…These agents allowed developers to predict how different players would traverse the map and make design decisions accordingly. The creation of playtesting agents has also been used to test board games [8], card games [9] and frameworks for the development of playtesting agents have been proposed [10], [11].…”

Section: Related Workmentioning

confidence: 99%

Agents for Automated User Experience Testing

Fernandes

Lopes

Prada

2021

2021 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW)

View full text Add to dashboard Cite

The automation of functional testing in software has allowed developers to continuously check for negative impacts on functionality throughout the iterative phases of development. This is not the case for User eXperience (UX), which has hitherto relied almost exclusively on testing with real users. User testing is a slow endeavour that can become a bottleneck for development of interactive systems. To address this problem, we here propose an agent based approach for automatic UX testing. We develop agents with basic problem solving skills and a core affect model, allowing us to model an artificial affective state as they traverse different levels of a game. Although this research is still at a primordial state, we believe the results here presented make a strong case for the use of intelligent agents endowed with affective computing models for automating UX testing.

show abstract

“…The study of believable agents defines a core aim of affective studies and human-computer interaction at large. Not only can believable agents improve the realism of the interaction, but they can be used for human-like automatic testing [1], compete in a game like humans would do [2], [3], collaborate for solving a task [4], or guide humans through a process that may include anything from visiting a (virtual) museum all the way to a virtual therapy session. The believability of such agents is generally defined in terms of their behavior [5] and is predominately associated with "human-like" decisions, manifestations or expressions.…”

Section: Introductionmentioning

confidence: 99%