A New Challenge: Approaching Tetris Link with AI
This work introduces a new challenge for the AI research community by analyzing a previously unstudied game, but it is incremental as it applies existing methods without major breakthroughs.
The paper tackled the problem of developing AI for the board game Tetris Link, which lacks prior scientific analysis, and found that a heuristic approach outperformed reinforcement learning and Monte Carlo tree search methods, though it still lost to experienced human players.
Decades of research have been invested in making computer programs for playing games such as Chess and Go. This paper focuses on a new game, Tetris Link, a board game that is still lacking any scientific analysis. Tetris Link has a large branching factor, hampering a traditional heuristic planning approach. We explore heuristic planning and two other approaches: Reinforcement Learning, Monte Carlo tree search. We document our approach and report on their relative performance in a tournament. Curiously, the heuristic approach is stronger than the planning/learning approaches. However, experienced human players easily win the majority of the matches against the heuristic planning AIs. We, therefore, surmise that Tetris Link is more difficult than expected. We offer our findings to the community as a challenge to improve upon.