AI in Human-computer Gaming: Techniques, Challenges and Opportunities

Yin, Qiyue; Yang, Jing; Huang, Kaiqi; Zhao, Ming; Ni, Wancheng; Liang, Bin; Huang, Yan; Wu, Shu; Wang, Liang

doi:10.48550/arxiv.2111.07631

Cited by 3 publications

(6 citation statements)

References 49 publications

(65 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FDM enhances the generalization capabilities of game AI due to its strong multi-modal and multi-task performance. DRL methods have achieved significant advancements in game AI, with examples such as the DQN agent [69] , AlphaGo [70] , Libratus [71] , OpenAI Five [72] , and AlphaStar [23] , where DRL agents have defeated professional human players. These successes indicate DRL's capacity to solve highly complex games [73] .…”

Section: Game Aimentioning

confidence: 99%

See 1 more Smart Citation

On Realization of Intelligent Decision Making in the Real World: A Foundation Decision Model Perspective

Wen,

Wan,

Zhou

et al. 2023

CAAI Artificial Intelligence Research

View full text Add to dashboard Cite

The pervasive uncertainty and dynamic nature of real-world environments present significant challenges for the widespread implementation of machine-driven Intelligent Decision-Making (IDM) systems. Consequently, IDM should possess the ability to continuously acquire new skills and effectively generalize across a broad range of applications. The advancement of Artificial General Intelligence (AGI) that transcends task and application boundaries is critical for enhancing IDM. Recent studies have extensively investigated the Transformer neural architecture as a foundational model for various tasks, including computer vision, natural language processing, and reinforcement learning. We propose that a Foundation Decision Model (FDM) can be developed by formulating diverse decision-making tasks as sequence decoding tasks using the Transformer architecture, offering a promising solution for expanding IDM applications in complex real-world situations. In this paper, we discuss the efficiency and generalization improvements offered by a foundation decision model for IDM and explore its potential applications in multi-agent game AI, production scheduling, and robotics tasks. Lastly, we present a case study demonstrating our FDM implementation, DigitalBrain (DB1) with 1.3 billion parameters, achieving human-level performance in 870 tasks, such as text generation, image captioning, video game playing, robotic control, and traveling salesman problems. As a foundation decision model, DB1 represents an initial step toward more autonomous and efficient real-world IDM applications.

show abstract

Section: Game Aimentioning

confidence: 99%

“…• Meta-World [87] is a suite of environments for benchmarking meta-reinforcement learning and multi-task learning. We collect data from all training and test tasks in the MT1 mode by training an APPO agent [72] from sample-factory repository [88] . For this task suite, we collect 88.2 thousand episodes in total.…”

Section: Simulated Control Tasksmentioning

confidence: 99%

On Realization of Intelligent Decision Making in the Real World: A Foundation Decision Model Perspective

Wen,

Wan,

Zhou

et al. 2023

CAAI Artificial Intelligence Research

View full text Add to dashboard Cite

show abstract

“…Aside from deterministic methods, AI approaches have achieved great success in II-SSGs based on reinforcement learning, deep neural networks and so on [106], [120], [127]- [138], for instance, Al-phaGo (the first AI agent to achieve superhuman level in Go) [10], AlphaZero (with initial training independent of human data and Go-specific features, reaching stateof-the-art performance in Go, Chess and Shogi with minimal domain knowledge) [11], and DeepStack [106], to name a few. More details can refer to a recent survey for AI in games [139]. Note that other closely related research subsumes imperfect-information general-sum games with full and bandit feedback [140]- [142], twoplayer zero-sum Markov games [143], and multi-player general-sum Markov games [144].…”

Section: A Zero-sum Games (Zsgs)mentioning

confidence: 99%

“…Recent years have witnessed great progress in the success of AI methods applied in games, which can integrate some advanced approaches of reinforcement learning, neural networks, meta-learning, and so on [135], [282]- [284]. With the advent of modern high-tech and big-data complex missions, AI methods provide an effective manner to commit real-time strategies by solely exploiting offline or real-time streaming data [139].…”

Section: Possible Future Directionsmentioning

confidence: 99%

A Survey of Decision Making in Adversarial Games

Li¹,

Mao²,

Ye³

et al. 2022

Preprint

View full text Add to dashboard Cite

Game theory has by now found numerous applications in various fields, including economics, industry, jurisprudence, and artificial intelligence, where each player only cares about its own interest in a noncooperative or cooperative manner, but without obvious malice to other players. However, in many practical applications, such as poker, chess, evader pursuing, drug interdiction, coast guard, cyber-security, and national defense, players often have apparently adversarial stances, that is, selfish actions of each player inevitably or intentionally inflict loss or wreak havoc on other players. Along this line, this paper provides a systematic survey on three main game models widely employed in adversarial games, i.e., zero-sum normal-form and extensive-form games, Stackelberg (security) games, zero-sum differential games, from an array of perspectives, including basic knowledge of game models, (approximate) equilibrium concepts, problem classifications, research frontiers, (approximate) optimal strategy seeking techniques, prevailing algorithms, and practical applications. Finally, promising future research directions are also discussed for relevant adversarial games.

show abstract

“…Since the start, video games have been a testing ground for Artificial Intelligence (AI) [2]. There have been many breakthroughs in AI stemming from the research on video games [3]. The rise in the popularity of games is the reason that game developers are looking to expand their audience.…”

Section: Introductionmentioning

confidence: 99%

DareFightingICE Competition: A Fighting Game Sound Design and AI Competition

Khan¹,

Nguyen²,

Dai³

et al. 2022

Preprint

View full text Add to dashboard Cite

This paper presents a new competition -at the 2022 IEEE Conference on Games (CoG) -called DareFightingICE Competition. The competition has two tracks: a sound design track and an AI track. The game platform for this competition is also called DareFightingICE, a fighting game platform. Dare-FightingICE is a sound-design-enhanced version of FightingICE, used earlier in a competition at CoG until 2021 to promote artificial intelligence (AI) research in fighting games. In the sound design track, participants compete for the best sound design, given the default sound design of DareFightingICE as a sample. Participants of the AI track are asked to develop their AI algorithm that controls a character given only sound as the input (blind AI) to fight against their opponent; a sample deep-learning blind AI will be provided by us. Our means to maximize the synergy between the two tracks are also described. This competition serves to come up with effective sound designs for visually impaired players, a group in the gaming community which has been mostly ignored. To the best of our knowledge, DareFightingICE Competition is the first of its kind within and outside of CoG.

show abstract

AI in Human-computer Gaming: Techniques, Challenges and Opportunities

Cited by 3 publications

References 49 publications

On Realization of Intelligent Decision Making in the Real World: A Foundation Decision Model Perspective

On Realization of Intelligent Decision Making in the Real World: A Foundation Decision Model Perspective

A Survey of Decision Making in Adversarial Games

DareFightingICE Competition: A Fighting Game Sound Design and AI Competition

Contact Info

Product

Resources

About