37. DQNによるアタリゲーム学習過程
Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves,
Ioannis Antonoglou, Daan Wierstra, Martin Riedmiller (DeepMind Technologies)
Playing Atari with Deep Reinforcement Learning
http://www.cs.toronto.edu/~vmnih/docs/dqn.pdf
https://www.youtube.com/watch?v=5WXVJ1A0k6Q
38. • Pπ ロールアウトポリシー(ロールアウトで討つ手を決める。Pπ(a|s) sという状態でaを討つ確率)
• Pσ Supervised Learning Network プロの討つ手からその手を討つ確率を決める。Pσ(a|s)sという状態でaを討
つ確率。
• Pρ 強化学習ネットワーク。Pρ(学習済み)に初期化。
• Vθ(s’) 局面の状態 S’ を見たときに、勝敗の確率を予測する関数。つまり、勝つか、負けるかを返します。
Mastering the game of Go with deep neural networks and tree search
http://www.nature.com/nature/journal/v529/n7587/full/nature16961.html
https://deepmind.com/research/alphago/
DEEP MIND社:DQNによるアタリゲーム学習過程
39. Deep Mind社 「Agent 57」
• Atariの古典的なゲーム57個を人間よりうまくプレイできるよう
になった Deep Mind社のAI
• https://deepmind.com/blog/article/Agent57-Outperforming-
the-human-Atari-benchmark
48. Enhancing Game Experiences with Character AI
Andrew Moran, Jordan Carlton(Magic Leap, Magic Leap/Weta Workshop)
https://gdcvault.com/play/1025829/Magic-Leap-Enhancing-Game-Experiences
49. Enhancing Game Experiences with Character AI
Andrew Moran, Jordan Carlton(Magic Leap, Magic Leap/Weta Workshop)
https://gdcvault.com/play/1025829/Magic-Leap-Enhancing-Game-Experiences
74. Deep Mind: Capture the flag
• Deep Mind社が行っている「旗取りゲーム」のプラットフォーム
• 現在は人間よりも圧倒的に強くなってしまった
• 人間が見つけた戦略を、AIがみつけている
• Quake III のエンジンを使用
• マップは自動生成
Deep Mind: Capture the Flag: the emergence of complex cooperative agents
https://deepmind.com/blog/article/capture-the-flag-science
75. • https://deepmind.com/blog
/capture-the-flag/
• Multi agnet learning
Deep Mind: Capture the Flag: the emergence of complex cooperative agents
https://deepmind.com/blog/article/capture-the-flag-science
Deep Mind: Capture the flag
76. Two Agent Cooperation by DeepMind
Deep Mind: Capture the Flag: the emergence of complex cooperative agents
https://deepmind.com/blog/article/capture-the-flag-science
77. Deep Mind: Capture the flag
Deep Mind: Capture the Flag: the emergence of complex cooperative agents
https://deepmind.com/blog/article/capture-the-flag-science
87. Microsoft: TextWorld
• マイクロソフトが構築したテキストアドベンチャーの学習環境
• 50ほどのテキストアドベンチャーを内包している
• TextWorld: A Learning Environment for Text-based Games
• https://arxiv.org/abs/1806.11532
•
• TextWorld: A learning environment for training reinforcement learning agents,
inspired by text-based games
• https://www.microsoft.com/en-us/research/blog/textworld-a-learning-
environment-for-training-reinforcement-learning-agents-inspired-by-text-
based-games/
•
• Getting Started with TextWorld
• https://www.youtube.com/watch?v=WVIIigrPUJs
96. Assassin’s Creed Origin の事例
• スクリプトによるオブジェクト同士の干渉テスト
• キャラクターの生成ポイントと配置オブジェクトの干渉テスト
• スクリプトによるテスト
'Assassin's Creed Origins': Monitoring and Validation of World Design Data
Nicholas Routhier
Ubisoft Montreal
http://www.gdcvault.com/play/1025054/-Assassin-s-Creed-Origins
102. Deep Learning: Beyond the Hype, Magnus Nordin Electronic Arts
https://www.gdcvault.com/play/1025098/Deep-Learning-Beyond-the
EA SEED
https://www.ea.com/seed/news/seed-imitation-learning-concurrent-actions
https://www.ea.com/seed/news/self-learning-agents-play-bf1
AIエージェントに「バトルフィールド 1」のプレイを教えるには?
https://www.ea.com/ja-jp/news/teaching-ai-agents-battlefield-1
Experimental Self-Learning AI in Battlefield 1
https://www.youtube.com/watch?v=ZZsSx6kAi6Y
Deep Learning in Battlefield One
103. Deep Learning in Battlefield One
https://www.ea.com/seed/news/seed-imitation-learning-concurrent-actions
https://www.ea.com/seed/news/self-learning-agents-play-bf1
https://www.youtube.com/watch?v=ZZsSx6kAi6Y
Deep Learning: Beyond the Hype, Magnus Nordin Electronic Arts
https://www.gdcvault.com/play/1025098/Deep-Learning-Beyond-the
EA SEED
https://www.ea.com/seed/news/seed-imitation-learning-concurrent-actions
https://www.ea.com/seed/news/self-learning-agents-play-bf1