New research published in Machine Learning shows pattern learning is not enough to train AI to tackle games—and abstract representations or hybrid approaches may help. Many AI researchers describe game-playing as the "Formula 1" of AI: it's a controlled test environment with clear rules and clear success criteria. This paper uses that idea as a diagnostic, by studying a very simple game Nim, a children's matchstick game whose optimal strategy is known exactly.
AI’s game-playing still has flaws: AlphaZero-style self-play tested on Nim
