A World Championship Caliber Checkers Program

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning (2019, background): “With the advent of agents capable of superhuman performance in Othello, Checkers (Schaeffer et al. 1992), Chess (Hsu et al. 1990) and Go (Silver et al. 2016), the challenges of this type of games is increasingly seen as exhausted.”
Playing SNES in the Retro Learning Environment (2016, background): “Traditionally, games were used as a RL environment, dating back to Chess (Campbell et al., 2002), Checkers (Schaeffer et al., 1992), backgammon (Tesauro, 1995) and the more recent Go (Silver et al., 2016).”
Reinforcement Learning of Local Shape in the Game of Go (2007, methodology): “Minimax search variants are particularly effective in Chess, Checkers, Othello and Backgammon [3; 7; 2; 13], whereas Monte-Carlo simulation has proven most successful in Scrabble [9] and Hearts [11].”
AndroidEnv: A Reinforcement Learning Platform for Android (2021, methodology): “RL methods have demonstrated success not only in game playing, for example checkers (Schaeffer et al., 1992), chess (Campbell et al., 2002; Silver et al., 2018), Go (Silver et al., 2016), poker (Moravčík et al., 2017), Atari (Mnih et al., 2015) and Starcraft II (Vinyals et al., 2019), but also in…”
An Analysis of Forward Pruning (1994, methodology): “This approach has worked well in games such as chess [3, 7], checkers [15, 14], and othello [6].”