1 / 17

General Game Playing (GGP)

General Game Playing (GGP). Marco Adelfio CMSC 828N – Spring 2009. Classic Game Playing AI. Deep Blue. TD-Gammon. Poki. General Game Playing AI. GGP Agent. General Game Playing. GGP Goals: Create systems to play arbitrary games (given formal game definitions)

landon
Télécharger la présentation

General Game Playing (GGP)

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. General Game Playing (GGP) Marco Adelfio CMSC 828N – Spring 2009

  2. Classic Game Playing AI Deep Blue TD-Gammon Poki

  3. General Game Playing AI GGP Agent

  4. General Game Playing • GGP Goals: • Create systems to play arbitrary games (given formal game definitions) • Eliminate game-specific strategies • Emphasize generic strategy formulation • Competition created by Stanford Logic Group • Hosted during AAAI conference since 2005 • $10,000 Grand Prize

  5. General Game Playing • Questions: • What additional challenges arise for GGP agents? • How should a GGP agent evaluate game states? • Can a GGP agent transfer knowledge between games?

  6. General Game Playing • Finitely many players, states • Game play controlled by Game Manager over network • Players act synchronously (noops allowed) • Time limits enforced • Basic agent must: • Understand rule specification • Respond to game states with legal actions • Recognize a terminal state and its payoffs

  7. Game Definition Language • A game definition must logically define: • Set of states in the game • Legal actions for each player from a given game state • Transition function • Initial state • Terminal states and their payoffs

  8. Game Definition Language - Example (role p1) (role p2) (init (cell 1 1 b)) (init (cell 1 2 b)) … (init (control p1) … (<= (legal ?w (mark ?x ?y)) (true (cell ?x ?y b)) (true (control ?w))) … (<= (next (cell ?m ?n x)) (does p1 (mark ?m ?n)) (true (cell ?m ?n b))) … (<= (row ?m ?x) (true (cell ?m 1 ?x)) (true (cell ?m 2 ?x)) (true (cell ?m 3 ?x))) … (<= (line ?x) (row ?m ?x)) (<= (line ?x) (column ?m ?x)) (<= (line ?x) (diagonal ?x)) … (<= (goal p1 100) (line x)) (<= (goal p1 0) (line o) … (<= terminal (line x))

  9. Game Communication

  10. General Game Playing • Design Challenges: • Indeterminacy • Size • Multi-game Commonalities • Opponent Recognition

  11. AAAI Competition – Past Winners • 2005 - ClunePlayer (UCLA) • 2006 - FluxPlayer (Technical University of Dresden) • 2007 - CADIA (Reykjavik University) • 2008 - CADIA (Reykjavik University)

  12. Agent 1: ClunePlayer • Approach: Minimax • Problem: Needs to assign values to intermediate game states in arbitrary games. • Solution: • Calculate a vector of generic features at each node • Simulate games to determine which features are “stable” and correlated with either payoff or control • When running minimax, use a combination of those scores as the evaluation heuristic

  13. Agent 2: CADIA-Player • Approach: UCT (Variant of Monte Carlo simulation) • Monte Carlo: • Pick random actions for each player to descend the tree • After reaching a terminal state, update expected payoff Q(s,a) for each visited state s and action a • Introduces explore/exploit tradeoff

  14. Agent 2: CADIA-Player • UCT (Upper Confidence bound for Trees) • Balance exploration and exploitation • Give “bonus” to less travelled paths

  15. Agent 3: UTexas LARG • Approach: Knowledge Transfer • Uses lessons from past games to improve play in new games • War Games! • Determines whether a new game is isomorphic or similar to a previous game. If so, transfer estimated rewards

  16. Summary • General Game Playing introduces a different set of challenges than designing game-specific AI • Biggest challenge is evaluating states in a novel game • Better understanding of general strategy formation has many applications

  17. References • GGP Website: http://games.stanford.edu/ • Hilmar Finnson. CADIA-Player: A General Game Playing Agent. MSc Thesis, School of Computer Science, Reykjavik University. 2007. • Kuhlmann, Gregory and Peter Stone. Graph-Based Domain Mapping for Transfer Learning in General Games. Lecture Notes in Computer Science, Volume 4701/2007.

More Related