Awesome AI in Game

Note: A daily compilation of fascinating AI insights, perfect for enhancing game development or gameplay to meet personal requirements. 🎮🤖 (Generated by Microsoft Copilot 😊)

Feel free to open an issue or shoot me an email if you come across any interesting papers, projects, researchers, or if you find that my understanding is not correct.

Table of Contents

Paper

• Survey
• Game Making
  • Animation
• Game Environment
  • PCG
  • Playable Video Generation
• Game Agent: To be a better man
  • Text-based
  • FPS
• Misc

Environment

• RPG

Project

• LLM

Paper

Survey

Note

Highlight Authors

• Julian Togelius Homepage Google Scholar

• Large Language Models and Games: A Survey and Roadmap Arxiv
  • Roberto Gallotta, Graham Todd, Marvin Zammit, Sam Earle, Antonios Liapis, Julian Togelius, Georgios N. Yannakakis
  • 28 Feb 2024

Game Making

Animation

Note

Highlight Authors

• Xue Bin (Jason) Peng Homepage Google Scholar
• Michiel van de Panne Homepage Google Scholar
• C. Karen Liu Lab Page Google Scholar
• Zhaoming Xie Homepage Google Scholar
• Sebastian Starke Homepage Google Scholar Super cool Homepage!!!

• Interactive Character Control with Auto-Regressive Motion Diffusion Models Arxiv, Project

  • Yi Shi, Jingbo Wang, Xuekun Jiang, Bingkun Lin, Bo Dai, Xue Bin Peng
  • Date: 16 Aug 2024
  • Summary: Propose an auto-regressive diffusion model for kinematic motion synthesis and conduct extensive experiments and comparisons to demonstrate the superiority of this method.
  • Data: 100STYLE, AMASS, LaFAN1
  • Metrics: APD(Average Pairwise Distance), ADE(Average Displacement Error), FDE(Final Displacement Error), Bone Length Error, Pen.Freq(foot penetration frequency), Pen.Dist(average foot penetration distance), FS(foot sliding), Jnt.Accel(joint acceleration)

• A Survey on Reinforcement Learning Methods in Character Animation Arxiv

  • Kwiatkowski, Ariel and Alvarado, Eduardo and Kalogeiton, Vicky and Liu, C. Karen and Pettré, Julien and van de Panne, Michiel and Cani, Marie‐Paule
  • 7 Mar 2022

• DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills Arxiv

  • Peng, Xue Bin and Abbeel, Pieter and Levine, Sergey and van de Panne, Michiel
  • 27 Jul 2018

Game Environment

PCG (Procedural Content Generation)

• Procedural Content Generation via Machine Learning (PCGML) Arxiv
  • Adam Summerville, Sam Snodgrass, Matthew Guzdial, Christoffer Holmgård, Amy K. Hoover, Aaron Isaksen, Andy Nealen, Julian Togelius
  • Date: 7 May 2018
  • Summary: Survey paper on procedural content generation via machine learning, including traditional methods, machine learning methods, use cases and open problems.

Playable Video Generation

• Diffusion Models Are Real-Time Game Engines Arxiv, Project

  • Dani Valevski, Yaniv Leviathan, Moab Arar, Shlomi Fruchter
  • Date: 27 Aug 2024
  • Summary: GameNGen, the first game engine powered entirely by a neural model that enables real-time interaction with a complex environment over long trajec- tories at high quality.
  • Data: VisDoom + RL
  • Metrics: PSNR, LPIPS, Human Eval

• Genie: Generative Interactive Environments Arxiv, Project

  • Jake Bruce, Michael Dennis, Ashley Edwards, Jack Parker-Holder, Yuge (Jimmy) Shi and more (DeepMind, UBC)
  • Date: 23 Feb 2024
  • Summary: The first generative interactive environment trained in an unsupervised manner from unlabelled Internet videos. The model can be prompted to generate an endless variety of action-controllable virtual worlds described through text, synthetic images, photographs, and even sketches.
  • Data: Platformer game videos from Youtube; Robotics datasets used in RT1
  • Metrics
    • FVD
    • delta-t PSNR: PSNR(x_t, x_t_hat) - PSNR(x_t, x_t_random)

Game Agent

To be a better man

Text-based

• Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf Arxiv
  • Yuzhuang Xu, Shuo Wang, Peng Li, Fuwen Luo, Xiaolong Wang, Weidong Liu, Yang Liu
  • 9 Sep 2023

FPS

• Counter-Strike Deathmatch with Large-Scale Behavioural Cloning Arxiv, Code

  • Tim Pearce, Jun Zhu
  • 9 Apr 2021

• Will GPT-4 Run DOOM? Arxiv, Project, Code

  • Adrian de Wynter
  • 8 Mar 2024

• Diplomacy Cicero and Diplodocus Code, Blog

  • Human-level play in the game of Diplomacy by combining language models with strategic reasoning Paper
    • Meta, CMU, Stanford, MIT, Columbia University, UCB, Harvard
    • 22 Nov 2022
    • Zhihu Blog about this paper
  • Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning Arxiv
    • Anton Bakhtin, David J Wu, Adam Lerer, Jonathan Gray, Athul Paul Jacob, Gabriele Farina, Alexander H Miller, Noam Brown
    • 11 Oct 2022

Misc

• Choose Your Weapon: Survival Strategies for Depressed AI Academics Arxiv
  • Julian Togelius, Georgios N. Yannakakis
  • 8 Feb 2024

Environment

RPG

• PokemonRedExperiments
  • Github: link
  • An awesome youtube video about this project by the author: link

Project

LLM

• LLM Riddles
  • blog from the author: 大模型解谜游戏 LLM Riddles的历程
  • gradio demo by ModelScope: link
  • opensource implementation by OpenDILab: link

Acknowledgement

• Multimodal & Large Language Models: The structure of our page is organized according to the layout of this page.