LAGOS--Nigeria is beating the West at its own word game, using a strategy that sounds like Scrabble sacrilege. By relentlessly studying short words, this country of 500 languages has risen to dominate English's top lexical contest. Last November, for the final of Scrabble's 32-round World Championship in Australia, Nigeria's winningest wordsmith, Wellington Jighere, defeated Britain's Lewis Mackay, in a victory that led morning news broadcasts in his homeland half a world away. It was the crowning achievement for a nation that boasts more top-200 Scrabble players than any other country, including the U.K., Nigeria's former colonizer and one of the board game's legacy powers. "In other countries they see it as a game," said Mr. Jighere, now a borderline celebrity and talent scout for one of the world's few government-backed national programs.
The current state-of-the-art Scrabble agents are not learning-based but depend on truncated Monte Carlo simulations and the quality of such agents is contingent upon the time available for running the simulations. This thesis takes steps towards building a learning-based Scrabble agent using self-play. Specifically, we try to find a better function approximation for the static evaluation function used in Scrabble which determines the move goodness at a given board configuration. In this work, we experimented with evolutionary algorithms and Bayesian Optimization to learn the weights for an approximate feature-based evaluation function. However, these optimization methods were not quite effective, which lead us to explore the given problem from an Imitation Learning point of view. We also tried to imitate the ranking of moves produced by the Quackle simulation agent using supervised learning with a neural network function approximator which takes the raw representation of the Scrabble board as the input instead of using only a fixed number of handcrafted features.
After a week in the desert, CES 2018 has finally come to a close. Booths were trod, products were demoed and the conference was visited by only one of the biblical plagues. Puffco debuted one of the only cannabis gadgets seen at CES in recent memory, a gaming robot beat virtually every human who challenged it in Scrabble, and Toyota's "E-Palette" mobility concept turned all of the heads.
Computing an effective strategy in games with incomplete information is much more difficult than in games where the status of every relevant factor is known. A weighted heuristic approach selects the move in a given position that maximizes a weighted sum of known factors, where the weights have been optimized over a large random sample of games. Probabilistic search is an alternative approach that generates a random set of scenarios, simulates how plausible moves perform under each scenario, and selects the move with the "best" overall performance. This paper compares the effectiveness of these approaches for the game of Scrabble.