Getting started with open source game playing AIs
1 like199 views
This document provides an introduction to open source game AIs, including Stockfish and Pachi for chess, and descriptions of common AI techniques like minimax search, Monte Carlo tree search, and sampling hidden information. It discusses optimal play, game trees, heuristic scores, cutoff thresholds, and the importance of testing AI changes. Examples are given for chess, Go, and Magic: The Gathering.
Getting started with open source game playing AIs
- 1. Getting started with Open Source Game AIs Melvin Zhang melvin@melvinzhang.net @melvinzhangzy Stockfish Pachi
- 4. https://en.wikipedia.org/wiki/Deep Blue (chess computer) Deep Blue
- 7. Optimal play Terminal min player max player
- 8. Optimal play 1 01 1 1Terminal min player max player
- 9. Optimal play 1 01 1 1 0 Terminal min player max player
- 10. Optimal play 1 01 1 1 0 1 Terminal min player max player
- 11. Optimal play 1 01 1 1 0 1 1 Terminal min player max player
- 12. Chess has about 1046 (2153 ) states!
- 13. Minimax algorithm with heuristic score Cut-off min player max player
- 14. Minimax algorithm with heuristic score .7 .1 .6 .9Cut-off min player max player
- 15. Minimax algorithm with heuristic score .7 .1 .6 .9 .1 Cut-off min player max player
- 16. Minimax algorithm with heuristic score .7 .1 .6 .9 .1 .6 Cut-off min player max player
- 17. Minimax algorithm with heuristic score .7 .1 .6 .9 .1 .6 .6 Cut-off min player max player
- 19. Heuristic scores are hard!
- 24. Monte Carlo evaluations Cut-off min player max player
- 25. Monte Carlo evaluations Cut-off min player max player
- 26. Monte Carlo evaluations Cut-off min player max player
- 27. Monte Carlo evaluations Cut-off min player max player
- 28. Monte Carlo evaluations Cut-off min player max player .7
- 29. Monte Carlo Tree Search (MCTS)
- 30. Some games have hidden information!
- 34. Choose a random instantiation of the hidden information during simulation
- 35. Theory Practice
- 36. Theory Practice • Optimal play • Minimax • Monte Carlo tree search • Sampling hidden information
- 37. Theory Practice • Optimal play • Minimax • Monte Carlo tree search • Sampling hidden information Stockfish Pachi