The grand challenge of computer Go

By Sylvain Gelly, Levente Kocsis, Marc Schoenauer, Michèle Sebag, David Silver, Csaba Szepesvari, Olivier Teytaud. 2012

240 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Economics and Econometrics

How researchers see this paper

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

In Artificial Intelligence

In Economics and Econometrics

Citations in the corpus

Deep Reinforcement Learning from Self-Play in Imperfect-Information Games (2016, background): “Games have a tradition of encouraging advances in artiﬁcial intelligence and machine learning (Samuel, 1959; Tesauro, 1995; Campbell et al., 2002; Gelly et al., 2012; Bowling et al., 2015).”
Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search (2012, methodology): “Nevertheless, the UCT algorithm has produced excellent empirical performance in many domains [12].”
Monte Carlo Tree Search: a review of recent modifications and applications (2021, background): “It was quickly called a major breakthrough (Gelly et al. 2012) as it allowed for a leap from 14 kyu, which is an average amateur level, to 5 dan, which is considered an advanced level but not professional yet.”
Neural Networks and Deep Learning (2018, unknown): “Subsequently, it was used in the game of Go [135, 346, 445, 446].”
Algorithms for computing strategies in two-player simultaneous move games (2016, unknown): “tical success in computer Go [47, 48], MCTS has since been applied successfully to simultaneous move games and to imperfect information games [49, 50, 13].”
Navigating the Affordance Landscape: Feedback Control as a Process Model of Behavior and Cognition. (2016, unknown): “Computational approaches to this problem usually adopt some sort of (learned) internal model and/or intermediate state values to guide the search; and some of them begin to be able to address large problem spaces, for example, Monte Carlo tree search [68,69].”
Convex Optimization: Algorithms and Complexity (2015, unknown): “In recent years, Monte-Carlo tree search methods have been applied with significant success to planning problems in games and other domains [Gelly et al., 2012].”
Self-play Monte-Carlo tree search in computer poker (2014, methodology): “Backgammon and computer Go are two examples of fully observable two-player games where reinforcement learning methods have achieved outstanding performance (Tesauro 1992; Gelly et al. 2012).”
Reinforcement learning improves behaviour from evaluative feedback (2015, methodology): “Use of the upper confidence intervals in trees (UCT) algorithm 26 resulted in a quantum leap in performance in Go 27 .”
Smooth UCT Search in Computer Poker (2015, methodology): “MCTS [Coulom, 2007] is a simulation-based search algorithm that has been incredibly successful in perfectinformation domains [Browne et al., 2012; Gelly et al., 2012].”
Bias-corrected Q-learning to control max-operator bias in Q-learning (2013, unknown): “Recently, a lot of attention has been given to look-ahead methods such as Monte Carlo Tree Search (MCTS) and Upper Confidence bounds applied to Trees (UCT) [21], [22].”
Mastering the game of Go with deep neural networks and tree search (2016, background): “The previous major breakthrough in computer Go, the introduction of MCTS, led to corresponding advances in many other domains; for example, general game-playing, classical planning, partially observed planning, scheduling, and constraint satisfaction 35,36 .”