Tetris is a fast-paced puzzle solving game that requires play-ers to rapidly maneuver falling blocks to clear rows and scorepoints. Skilled Tetris players learn to execute moves in thegame very quickly to keep up with the increasing time pres-sure. But world champion Tetris players employ more complexstrategies that save precious milliseconds that enable them toreach even higher levels of play. Such strategies show mas-tery of the game’s event structure, but also come with a startupcost— a “cognitive speed bump”— wherein they must mo-mentarily decide whether to rotate a block left or right, evenfor scenarios where the distinction is not meaningful for per-formance. We present data showing both the world champions’superior overall action times, but also a preliminary “speedbump” that is consistent both within and between world cham-pion players. Potential underlying memory structures are ex-plored, and implications are discussed for both the Soft Con-straints Hypothesis and the relationship between Hick’s Lawand expertise.

What can a machine learning simulation tell us about human performance in a complex, real-time task such as Tetris¬ó? Although Tetris is often used as a research tool (Mayer, 2014), the strategies and methods used by Tetris players have seldom been the explicit focus of study. In Study 1, we use cross-entropy reinforcement learning (CERL) (Szita & Lorincz, 2006; Thiery & Scherrer, 2009) to explore (a) the utility of high-level strategies (goals or objective functions) for maximizing performance and (b) a variety of features and feature-weights (methods) for optimizing a low-level, onezoid optimization strategy. Two of these optimization strategies quickly rise to performance plateaus, whereas two others continued towards higher but more jagged (i.e., variable) plateaus. In Study 2, we compare the zoid (i.e., Tetris piece) placement decisions made by our best CERL models with those made by the full spectrum of novice-to-expert human Tetris players. Across 370,131 episodes collected from 67 human players, the ability of two CERL strategies to classify human zoid placements varied with player expertise from 43% for our lowest scoring novice to around 65% for our three highest scoring experts.