Automated testing of computer games is a challenging problem, especially when
lengthy scenarios have to be tested. Automating such a scenario boils down to
finding the right sequence of interactions given an abstract description of the
scenario. Recent works have shown that an agent-based approach works well for
the purpose, e.g. due to agents' reactivity, hence enabling a test agent to
immediately react to game events and changing state. Many games nowadays are
multi-player. This opens up an interesting possibility to deploy multiple
cooperative test agents to test such a game, for example to speed up the
execution of multiple testing tasks. This paper offers a cooperative
multi-agent testing approach and a study of its performance based on a case
study on a 3D game called Lab Recruits.

自动测试计算机游戏是一个具有挑战性的问题，特别是当需要测试冗长的场景时。本文提出了一种合作多代理测试方法，并基于一个名为实验室招募的 3D 游戏的案例研究，对其性能进行了研究。

自动化电子游戏测试的多智能体合作方法

Cooperative Multi-agent Approach for Automated Computer Game Testing

Computer games are widespread nowadays and enjoyed by people of all ages. But
when it comes to kids, playing these games can be more than just fun, it is a
way for them to develop important skills and build emotional intelligence.
Facial expressions and sounds that kids produce during gameplay reflect their
feelings, thoughts, and moods. In this paper, we propose a novel framework that
integrates a fuzzy approach for the recognition of emotions through the
analysis of audio and video data. Our focus lies within the specific context of
computer games tailored for children, aiming to enhance their overall user
experience. We use the FER dataset to detect facial emotions in video frames
recorded from the screen during the game. For the audio emotion recognition of
sounds a kid produces during the game, we use CREMA-D, TESS, RAVDESS, and Savee
datasets. Next, a fuzzy inference system is used for the fusion of results.
Besides this, our system can detect emotion stability and emotion diversity
during gameplay, which, together with prevailing emotion report, can serve as
valuable information for parents worrying about the effect of certain games on
their kids. The proposed approach has shown promising results in the
preliminary experiments we conducted, involving 3 different video games, namely
fighting, racing, and logic games, and providing emotion-tracking results for
kids in each game. Our study can contribute to the advancement of
child-oriented game development, which is not only engaging but also accounts
for children's cognitive and emotional states.

提出了一个基于模糊推理系统的新框架，旨在通过音频和视频数据分析来识别儿童计算机游戏中的情绪，以提升儿童用户体验，并提供对情绪的跟踪结果，有助于儿童导向式游戏开发的进展。

儿童电脑游戏中的音视频情感识别模糊方法

Fuzzy Approach for Audio-Video Emotion Recognition in Computer Games for  Children

Wordle is a very popular word game that is owned by the New York Times. We
can design parameterized strategies for solving Wordle, based on probabilistic,
statistical, and information-theoretical information about the games. The
strategies can handle a reasonably large family of Wordle-like games both
systematically and dynamically, meaning that we do not rely on precomputations
that may work for non-fixed games. More specifically, the answer set can be
arbitrary, not confining to the current 2315 words. The answer words may
include any specific number of letters (does not have to be five), and the set
of symbols that form the words does not have to be limited to only the English
alphabet.
Exploring possible strategies for solving the Wordle-like games offers an
attractive learning challenges for students who are learning to design computer
games. This paper will provide the results of using two families of
parameterized strategies to solve the current Wordle, using the simulator that
abides by the hard-mode rules as the baseline. The baseline simulator used an
average of 4.078 guesses to find the 2315 answers, and needed more than six
trials to solve the game 1.77% of the time. The best performing strategy of
ours used an average of 3.674 guesses to find the 2315 answers, and failed
0.65% of the time.

本文介绍了用概率、统计和信息理论的方法，设计参数化策略来处理 Wordle 等电脑游戏，并探索两个家族参数化策略用于解决 Wordle，并与基准解决方案进行比较得到的结果。

利用 Wordle 进行学习，设计和比较策略

Using Wordle for Learning to Design and Compare Strategies

Modern day computer games have extremely large state and action spaces. To
detect bugs in these games' models, human testers play the games repeatedly to
explore the game and find errors in the games. Such gameplay is exhaustive and
time consuming. Moreover, since robotics simulators depend on similar methods
of model specification and debugging, the problem of finding errors in the
model is of interest to the robotics community to ensure robot behaviors and
interactions are consistent in simulators. Previous methods have used
reinforcement learning arXiv:2103.13798 and search based methods (Chang, 2019,
(Chang, 2021) arXiv:1811.06962 including Rapidly-exploring Random Trees (RRT)
to explore a game's state-action space to find bugs. However, such search and
exploration based methods are not efficient at exploring the state-action space
without a pre-defined heuristic. In this work we attempt to combine a
human-tester's expertise in solving games, and the RRT's exhaustiveness to
search a game's state space efficiently with high coverage. This paper
introduces Cloning Assisted RRT (CA-RRT) to test a game through search. We
compare our methods to two existing baselines: 1) a weighted-RRT as described
by arXiv:1812.03125; 2) human demonstration seeded RRT as described by Chang
et. al. We find CA-RRT is applicable to more game maps and explores more game
states in fewer tree expansions/iterations when compared to the existing
baselines. In each test, CA-RRT reached more states on average in the same
number of iterations as weighted-RRT. In our tested environments, CA-RRT
reached the same number of states as weighted-RRT by more than 5000 fewer
iterations on average, almost a 50% reduction and applied to more scenarios
than. Moreover, as a consequence of our first person behavior cloning approach,
CA-RRT worked on unseen game maps than just seeding the RRT with human
demonstrated states.

本文提出了一种能够通过结合人类测试人员的经验和快速扩展随机树（RRT）的极尽全面性来高效地搜索游戏状态空间的测试方法，并称作 Cloning Assisted RRT（CA-RRT），比传统的加权 RRT 和人类演示生成的 RRT 更适用于更多的游戏地图和测试环境，表现出更高的搜索效率。