Simulation-Based Approach to General Game Playing

By Hilmar Finnsson, Yngvi Björnsson. AAAI Conference on Artificial Intelligence, 2008

307 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/8cbcab8eacee75d4811ef38db83b124c3ecea084

How researchers see this paper

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

Citations in the corpus

Understanding Sampling Style Adversarial Search Methods (2012, methodology): “This also happens in the general game playing setting (Finnsson and Björnsson, 2008).”
Convergence of Monte Carlo Tree Search in Simultaneous Move Games (2013, methodology): “For practical applications and in situations with limited domain knowledge, variants of simulation-based algorithms such as Monte Carlo Tree Search (MCTS) are typically used in practice [10, 11, 12, 13].”
Variance Reduction in Monte-Carlo Tree Search (2011, unknown): “This general approach [6] has been successfully adapted to a variety of challenging problem settings, including Markov Decision Processes, Partially Observable Markov Decision Processes, Real-Time Strategy games, Computer Go and General Game Playing [15, 22, 2, 9, 12, 10].”
Multi-armed bandits with episode context (2011, methodology): “Following success in Go, UCT-based methods have been applied successfully to other domains [16, 18].”
Sidekick agents for sequential planning problems (2013, background): “As of June 2013, the dominant system in general game playing, which tests the ability of AI agents to play previously unseen games, is the MCTS-based system Cadiaplayer [8].”
The grand challenge of computer Go (2012, background): “The generality of MCTS is demonstrated by its recent dominance in the general game playing competition [14].”
AN ANALYSIS OF UCT IN MULTI-PLAYER GAMES (2008, methodology): “05 as in (Finnsson and Björnsson, 2008) to bias the selection of moves during random playouts.”
Monte-Carlo tree search and rapid action value estimation in computer Go (2011, unknown): “Monte-Carlo tree search [1] is a new paradigm for search, which has revolutionised computer Go [2] [3], and is rapidly replacing traditional search algorithms as the method of choice in challenging domains such as General Game Playing [4], Amazons [5], Lines of Action [6], multi-player card games [7”
Guiding Combinatorial Optimization with UCT (2012, background): “It has received much attention during the past few years due to its success in game playing agents, especially for Go [4, 5] and Kriegspiel [2], as well as for general game playing [3].”
Monte-Carlo Planning in Large POMDPs (2010, methodology): “It has outperformed previous planning approaches in challenging games such as Go [5], Amazons [10] and General Game Playing [4].”
A Survey of Monte Carlo Tree Search Methods (2012, methodology): “These have typically had success with single-player puzzles and similar optimisation tasks.”
X-Armed Bandits (2010, unknown): “In Section 5 we compare the results of this paper with previous works.”
Monte Carlo Tree Search: a review of recent modifications and applications (2021, methodology): “The concept of Information Sets has been introduced by Frank and Basin (1998). It is illustrated in Fig.”
Temporal-difference search in computer Go (2012, unknown): “…policy, has outperformed previous approaches to search in a variety of challenging games, including Go (Gelly et al. 2006), General Game Playing (Finnsson and Björnsson 2008), Amazons (Lorentz 2008), Lines of Action (Winands and Björnsson 2009), multi-player card games (Schäfer 2008; Sturtevant…”