Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Godoggo

511 views

Published on

  • Be the first to comment

  • Be the first to like this

Godoggo

  1. 1. GO DOG GO Robert Carr <racarr@gnome.org>Friday, April 15, 2011
  2. 2. GO DOG GO Robert Carr <racarr@gnome.org>Friday, April 15, 2011
  3. 3. GO?Friday, April 15, 2011
  4. 4. GOBJECT-DETECTOR • Go board recognition library. • Rewritten in C++ for Android NDK. • Some issues with OpenCv on Android...Friday, April 15, 2011
  5. 5. IMPROVED GRID DETECTION • Board has dots to indicate “Hoshi” points (For example Tengen at 10,10) • Adjust grid to fit better to Hoshi points.Friday, April 15, 2011
  6. 6. MORE? • Score boards. Requires a simple MonteCarlo AI or user interaction. • Live broadcasting to KGS.Friday, April 15, 2011
  7. 7. GIFU! • iTunes for your Go game records. • Fully queryable sqlite backed database. • Tested with collection of 50,000 games.Friday, April 15, 2011
  8. 8. TAGS AND COMMENTS • With a collection of 50,000 games it can be difficult to remember what you are studying...or which game had a particular move. • Would also be nice to comment game without disturbing the original file.Friday, April 15, 2011
  9. 9. SGF PRINTER • Would also be nice to print records in Kifu format.Friday, April 15, 2011
  10. 10. GO AI • Really hard :(Friday, April 15, 2011
  11. 11. BOARD REPRESENTATION • Keep track of blocks/ liberties. • Zobrist hashing • Positional Super Ko • Symmetry Checking.Friday, April 15, 2011
  12. 12. AI ARCHITECTURE • Multiple modules generate candidate moves. • Moves are evaluated by Monte Carlo evaluator.Friday, April 15, 2011
  13. 13. MONTE CARLO EVALUATOR • Core of AI move evaluation. • Randomly plays out thousands of games and calculates win percentage. • Playouts can be “light” or “heavy”Friday, April 15, 2011
  14. 14. PATTERN MATCHING • Match subset of board against pattern. • Recognize patterns independent of transposition, rotation, etc...Friday, April 15, 2011
  15. 15. FUSEKI DATABASE • Compiled from collection of pro and high dan amateur games. • Typically relevant for first 50 moves.Friday, April 15, 2011
  16. 16. JOSEKI DATABASE • Patterns in local corner positions. • Best moves found for both sides.Friday, April 15, 2011
  17. 17. CONNECTIVITY • Higher level concept than blocks. • The red stones are “connected” • Every shape has weaknesses.Friday, April 15, 2011
  18. 18. PROVERBIAL KNOWLEDGE • Black would like to play inbetween the white stones on top. • Proverbial knowledg says to build thickness first....pattern database has a suggestion!Friday, April 15, 2011
  19. 19. THE PEEPFriday, April 15, 2011
  20. 20. STRATEGIC DECISIONS • Proverbial knowledge database will enable guiding selection of moves for MonteCarlo based on moves generated by various strategy modules. • In previous example, “invasion” module, would query the “thickness” module for setup plays. • Such plays are given heavier play outs in MonteCarlo.Friday, April 15, 2011
  21. 21. QUESTIONS?Friday, April 15, 2011

×