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.
- 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
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!!!
- 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
-
MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting Arxiv
- Chen Tessler, Yunrong Guo, Ofir Nabati, Gal Chechik, Xue Bin Peng
- 22 Sep 2024
-
SuperPADL: Scaling Language-Directed Physics-Based Control with Progressive Supervised Distillation Arxiv
- Jordan Juravsky, Yunrong Guo, Sanja Fidler, Xue Bin Peng
- 15 Jul 2024
-
PADL: Language-Directed Physics-Based Character Control Arxiv
- Jordan Juravsky, Yunrong Guo, Sanja Fidler, Xue Bin Peng
- 30 Nov 2022
-
AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control Arxiv
- Xue Bin Peng, Ze Ma, Pieter Abbeel, Sergey Levine, Angjoo Kanazawa
- 5 Apr 2021
-
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
-
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: (AMDM) 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)
-
Human Motion Diffusion Model Arxiv
- Guy Tevet, Sigal Raab, Brian Gordon, Yonatan Shafir, Daniel Cohen-Or, Amit H. Bermano
- 29 Sep 2022
- Keywords: MDM
- 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.
-
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)
To be a better man
- 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
-
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
- Human-level play in the game of Diplomacy by combining language models with strategic reasoning Paper
- Choose Your Weapon: Survival Strategies for Depressed AI Academics
Arxiv
- Julian Togelius, Georgios N. Yannakakis
- 8 Feb 2024
- 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
- Multimodal & Large Language Models: The structure of our page is organized according to the layout of this page.