Upgrade to Pro — share decks privately, control downloads, hide ads and more …

PCGRL (Procedural Contents Generation via Machi...

PCGRL (Procedural Contents Generation via Machine Learning)

第79回 Machine Learning 15minutes! における講演資料です。

miyayou

July 30, 2023
Tweet

More Decks by miyayou

Other Decks in Programming

Transcript

  1. Rogue (1980)のダンジョン生成法 Rect[0] Rect[0] Rect[1] Rect[0] Rect[1] Rect[2] Rect[3] このようにアセット(ゲームのデータ)をツールなどを通して製作するのではなく、

    プログラムで作ることを「プロシージャル・コンテンツ・ジェネレーション」(PCG)と言う。 http://racanhack.sourceforge.jp/rhdoc/intromaze.html
  2. Far Cry 2 Dunia Engine - Growing Vegetation (Far Cry

    HQ) https://www.youtube.com/watch?v=FI3oR6vqn1Q
  3. L-system による街の自動生成 City Engine(central pictures) Yoav I H Parish, Pascal

    Müller http://www.centralpictures.com/ce/tp/paper.pdf http://www.centralpictures.com/ce/ George Kelly, Hugh McCabe, A Survey of Procedural Techniques for City Generation http://www.gamesitb.com/SurveyProcedural.pdf
  4. L-system による街の自動生成 City Engine(central pictures) Yoav I H Parish, Pascal

    Müller http://www.centralpictures.com/ce/tp/paper.pdf http://www.centralpictures.com/ce/ George Kelly, Hugh McCabe, A Survey of Procedural Techniques for City Generation http://www.gamesitb.com/SurveyProcedural.pdf
  5. 評価 選 択 交叉 突然変異 ルール チェック 整合性 がある か?

    ポリシー 選択 速度が 遅い? ゴミ 箱 テストプ レイ 前と似て いる 引き分け になり やすい 母集団 Mark J. Nelson, “Bibliography: Encoding and generating videogame mechanics”, IEEE CIG 2012 tutorial URL https://www.kmjn.org/notes/generating_mechanics_bibliography.html Cameron Browne,“Evolutionary Game Design”, SpringerBriefs in Computer Science, 2011 URL https://www.springer.com/jp/book/9781447121787
  6. PCGML PCGRL: Procedural Content Generation via Reinforcement Learning Ahmed Khalifa,

    Philip Bontrager, Sam Earle, Julian Togelius https://arxiv.org/abs/2001.09212
  7. PCGRL: Procedural Content Generation via Reinforcement Learning Ahmed Khalifa, Philip

    Bontrager, Sam Earle, Julian Togelius https://arxiv.org/abs/2001.09212
  8. PCGRL: Procedural Content Generation via Reinforcement Learning Ahmed Khalifa, Philip

    Bontrager, Sam Earle, Julian Togelius https://arxiv.org/abs/2001.09212
  9. PCGRL: Procedural Content Generation via Reinforcement Learning Ahmed Khalifa, Philip

    Bontrager, Sam Earle, Julian Togelius https://arxiv.org/abs/2001.09212
  10. PCGRL: Procedural Content Generation via Reinforcement Learning Ahmed Khalifa, Philip

    Bontrager, Sam Earle, Julian Togelius https://arxiv.org/abs/2001.09212 PCGRL参考 • https://twitter.com/togelius/status/1222038094507102208 • https://twitter.com/i/status/1222038094507102208
  11. CHAPTER 1 ゲームと知能研究 CHAPTER 2 不完全情報ゲーム CHAPTER 3 不確定ゲーム CHAPTER

    4 コミュニケーションゲーム CHAPTER 5 実環境のゲーム CHAPTER 6 ゲームデザイン CHAPTER 7 メタAIとプロシージャル コンテンツ ジェネレーション CHAPTER 8 人間らしさと楽しさの演出 CHAPTER 9 ゲーム体験の評価 CHAPTER 10 人間の認知機能とスキルアップの原理 CHAPTER 11 認知研究とAIの人間への影響 • 発売日2023/07/04 • 発行元オーム社
  12. PCGRL: Procedural Content Generation via Reinforcement Learning Ahmed Khalifa, Philip

    Bontrager, Sam Earle, Julian Togelius https://arxiv.org/abs/2001.09212
  13. 人間が製作し、 人工知能がチェックする Adversarial Reinforcement Learning for Procedural Content Generation Linus

    Gisslén, Andy Eakins, Camilo Gordillo, Joakim Bergdahl, Konrad Tollmar https://arxiv.org/abs/2103.04847
  14. Adversarial Reinforcement Learning for Procedural Content Generation Linus Gisslén, Andy

    Eakins, Camilo Gordillo, Joakim Bergdahl, Konrad Tollmar https://arxiv.org/abs/2103.04847
  15. Adversarial Reinforcement Learning for Procedural Content Generation Linus Gisslén, Andy

    Eakins, Camilo Gordillo, Joakim Bergdahl, Konrad Tollmar https://arxiv.org/abs/2103.04847
  16. Adversarial Reinforcement Learning for Procedural Content Generation Linus Gisslén, Andy

    Eakins, Camilo Gordillo, Joakim Bergdahl, Konrad Tollmar https://arxiv.org/abs/2103.04847
  17. CoG 2021: Adversarial Reinforcement Learning for Procedural Content Generation SEED

    – Electronic Arts https://www.youtube.com/watch?v=kNj0qcc6Fpg
  18. Adversarial Reinforcement Learning for Procedural Content Generation Linus Gisslén, Andy

    Eakins, Camilo Gordillo, Joakim Bergdahl, Konrad Tollmar https://arxiv.org/abs/2103.04847
  19. Adversarial Reinforcement Learning for Procedural Content Generation Linus Gisslén, Andy

    Eakins, Camilo Gordillo, Joakim Bergdahl, Konrad Tollmar https://arxiv.org/abs/2103.04847
  20. Adversarial Reinforcement Learning for Procedural Content Generation Linus Gisslén, Andy

    Eakins, Camilo Gordillo, Joakim Bergdahl, Konrad Tollmar https://arxiv.org/abs/2103.04847