XXII. Programming a Computer for Playing Chess 1

By Claude E. Shannon, Bell Telephone. 1950

Subfields: Game & Decision Theory, Algorithms & Complexity

How researchers see this paper

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

In Game & Decision Theory

In Algorithms & Complexity

Citations in the corpus

Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm (2017, background): “Babbage, Turing, Shannon, and von Neumann devised hardware, algorithms and theory to analyse and play the game of chess.”
Giraffe: Using Deep Reinforcement Learning to Play Chess (2015, methodology): “They are all based on the idea of the ﬁxed-depth minimax algorithm ﬁrst developed by John von Neumann in 1928 [4], and adapted for the problem of chess by Claude E. Shannon in 1950 [5].”
Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization (2021, background): “…persistent technical advances towards our ultimate goal of building intelligent agents like humans, from Shannon’s initial interest in Chess (Shannon, 1950) and IBM DeepBlue (Campbell et al., 2002), to the most recent deep reinforcement learning breakthroughs in Go (Silver et al., 2017),…”
Time and Space: Why Imperfect Information Games are Hard (2018, methodology): “Using algorithms which rely on decomposition(1) we have seen super-human play in games like chess (with 10(40)-10(50) reachable states [78]) and recently in the game of go [81] (with somewhat less than 10(171) reachable states [86].”
Large Language Models (2023, background): “Some famous and difficult “challenge tasks” include playing chess [122], proving mathematical theorems [104], and answering natural language questions using generally known facts and common sense.”
Unity: A General Platform for Intelligent Agents (2018, background): “This trend can be traced back to the earliest work in AI around playing games such as chess and checkers (Shannon, 1950; Samuel, 1959), or later work applying reinforcement learning to the game of Backgammon (Tesauro, 1995).”
Meta-modeling game for deriving theoretical-consistent, micro-structural-based traction-separation laws via deep reinforcement learning (2018, background): “This situation is similar of playing the games of chess and Go where the number of possible combinations of decisions or moves (each can be represented by a decision tree) remains finite but is so enormous that it is not possible to seek the optimal moves by exhausting all possibilities [Shannon, 19”