Techniques and Paradigms in Modern Game AI Systems

Lu, Yunlong; Li, Wenxin

doi:10.3390/a15080282

Cited by 11 publications

(7 citation statements)

References 79 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Voyager first leveraged leading large language model GPT-4, surpassing all prior Minecraft agents. Compared to previous algorithms, Voyager obtained the most items, progressed fastest in skills, and explored the widest [4]. Park et al built a virtual town with inhabitants driven by a large language model, enabling natural language interaction with players to create unprecedented general game AI [22].…”

Section: Artificial General Intelligence In Gamementioning

confidence: 99%

See 1 more Smart Citation

A research of artificial intelligence game agent application

Lan,

2024

ACE

View full text Add to dashboard Cite

Currently, large language models are on the rise with breakthrough progress in artificial intelligence. Existing reviews of AI game agents have not covered these latest developments, requiring a combing and analysis of the newest research advancements in game AI agents. This paper summarizes the application scenarios of game AI agents in four aspects: combat AI, Non-Player Character (NPC) interaction, automated testing, and Artificial General Intelligence (AGI) testing. In combat AI, there is a progressive developmental trend, with the introduction of Monte Carlo tree search and reinforcement learning enabling AI game agents to fully surpass humans in traditional board games. In NPC interaction, full AI is unnecessary. Game developers only need to incorporate AI for abilities related to player experience to increase appeal, with controllable generation results. In automated testing, game AI agents lack generalizability for testing so far. In AGI testing, academia has helpfully explored general game AI, but capabilities remain limited to certain games. Introducing large language models to game AI agents shows unprecedented capabilities. Finally, this paper provides an outlook on the hot topics and future directions of this research subject.

show abstract

Section: Artificial General Intelligence In Gamementioning

confidence: 99%

“…Instead, it combines multiple AI methods and enables general game intelligence with the support of multimodal models. However, existing review studies are mostly limited to board games and video games characterized by competition and strategy [4]. They have not covered survival games, leaving great potential for supplementary research.…”

Section: Introductionmentioning

confidence: 99%

A research of artificial intelligence game agent application

Lan,

2024

ACE

View full text Add to dashboard Cite

show abstract

“…• The survey of [51] systematically summarizes various adversarial game models and the corresponding strategy generation approaches from a game theory perspective, and provides some real-world applications such as security, poker and politics. • The survey of [52] focuses on a particular application in the decision-making domain, the game AI system, considering three typical modern AI games (perfect in- formation games, imperfect information games, and multiagent games), providing a review of the relative solving techniques, paradigms and applications.…”

Section: B Related Surveysmentioning

confidence: 99%

Transformer in Reinforcement Learning for Decision-Making: A Survey

Yuan¹,

Chen²,

Chen³

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>Reinforcement learning (RL) has become a dominant decision-making paradigm and has achieved notable success in many real-world applications, such as autonomous driving, robotic manipulation, robotic navigation and gaming AI. However, the powerful abilities of the RL variants were developed with advanced machine learning techniques. For example, deep neural networks play a crucial role in unlocking RL’s potential in large-scale decision-making tasks. Inspired by present day major successes of Transformer in natural language processing and computer vision, numerous bottlenecks have been overcome by combining Transformer with RL for decision-making. This paper presents a multiangle systematic survey of various Transformerbased RL (TransRL) models applied in decision-making tasks, including basic models, advanced algorithms, representative implementation instances, applications, and known challenges. Our work aims to provide insights into problems that inherently arise with the current RL approaches, and examines how we can address them with better TransRL models. To our knowledge, we are the first to present a comprehensive review of the recent Transformers research developments in RL for decisionmaking. We hope this survey provides a comprehensive review of TransRL models and also inspires the RL community in its pursuit of future directions. Finally, to keep track of the rapid TransRL developments in the decision-making domains, we summarize the latest relevant papers and their open-source implementations at https://github.com/williamyuanv0/Transformerin-Reinforcement-Learning-for-Decision-Making-A-Survey.</p>

show abstract

“…In recent years, with the continuous development and progress in the field of artificial intelligence, AI has achieved remarkable success in many areas, even surpassing human performance in scenarios such as board games and electronic games [1]. In the field of reinforcement learning, offline reinforcement learning is a crucial research area.…”

Section: Introductionmentioning

confidence: 99%

Optimizing Reinforcement Learning Using a Generative Action-Translator Transformer

Li,

Xie,

Zhao

2024

Algorithms

View full text Add to dashboard Cite

In recent years, with the rapid advancements in Natural Language Processing (NLP) technologies, large models have become widespread. Traditional reinforcement learning algorithms have also started experimenting with language models to optimize training. However, they still fundamentally rely on the Markov Decision Process (MDP) for reinforcement learning, and do not fully exploit the advantages of language models for dealing with long sequences of problems. The Decision Transformer (DT) introduced in 2021 is the initial effort to completely transform the reinforcement learning problem into a challenge within the NLP domain. It attempts to use text generation techniques to create reinforcement learning trajectories, addressing the issue of finding optimal trajectories. However, the article places the training trajectory data of reinforcement learning directly into a basic language model for training. Its aim is to predict the entire trajectory, encompassing state and reward information. This approach deviates from the reinforcement learning training objective of finding the optimal action. Furthermore, it generates redundant information in the output, impacting the final training effectiveness of the agent. This paper proposes a more reasonable network model structure, the Action-Translator Transformer (ATT), to predict only the next action of the agent. This makes the language model more interpretable for the reinforcement learning problem. We test our model in simulated gaming scenarios and compare it with current mainstream methods in the offline reinforcement learning field. Based on the presented experimental results, our model demonstrates superior performance. We hope that introducing this model will inspire new ideas and solutions for combining language models and reinforcement learning, providing fresh perspectives for offline reinforcement learning research.

show abstract

Techniques and Paradigms in Modern Game AI Systems

Cited by 11 publications

References 79 publications

A research of artificial intelligence game agent application

A research of artificial intelligence game agent application

Transformer in Reinforcement Learning for Decision-Making: A Survey

Optimizing Reinforcement Learning Using a Generative Action-Translator Transformer

Contact Info

Product

Resources

About