General Game Playing: Overview of the AAAI Competition

By M. Genesereth, Nathaniel Love, Barney Pell. 2005

589 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Evaluation & Benchmarks

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 Computer Vision and Pattern Recognition

In Evaluation & Benchmarks

Citations in the corpus

The Arcade Learning Environment: An Evaluation Platform for General Agents (2012, background): “His work strongly influenced the design of the now annual General Game Playing competition (Genesereth et al., 2005). Our framework differs in that we do not assume to have access to a compact logical description of the game semantics. Schaul, Togelius, and Schmidhuber (2011) also recently presented”
Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm (2017, background): “However, these systems are highly tuned to their domain, and cannot be generalised to other problems without significant human effort, while general game-playing systems (12, 25) remain comparatively weak.”
Thinking Fast and Slow with Deep Learning and Tree Search (2017, background): “It is behind the leading algorithms in the AAAI general game playing competition [9].”
OpenSpiel: A Framework for Reinforcement Learning in Games (2019, background): “The purpose of OpenSpiel is to promote general multiagent reinforcement learning across many different game types, in a similar way as general game-playing [21] but with a heavy emphasis on learning and not in competition form.”
A Roadmap Towards Machine Intelligence (2015, background): “This roadmap constitutes only the beginning of a long journey towards AI, and we hope other researchers will be joining it in pursuing the goals it outlined.”
TextWorld: A Learning Environment for Text-based Games (2018, methodology): “In future work our aim is to integrate the TextWorld framework with well established frameworks such as GDL [Genesereth et al., 2005] or STRIPS [Fikes and Nilsson, 1971].”
Text-based adventures of the golovin AI agent (2017, background): “Currently, there are two main, well-established GGP domains providing their own game specification languages and competitions [4].”
Simulation-Based Approach to General Game Playing (2008, background): “The GGP Competition (Genesereth, Love, & Pell 2005) was founded as an initiative to facilitate further research into this area.”
Convergence of Monte Carlo Tree Search in Simultaneous Move Games (2013, background): “Many well-known games are instances of this class, including card games such as Goofspiel [3, 4], variants of pursuit-evasion games [5], and several games from general game-playing competition [6].”
A Neuroevolution Approach to General Atari Game Playing (2014, background): “In summary, the large number of games, availability of highquality emulators, and the standardized interface make the Atari 2600 a great stepping stone from board games and declarative games [like those used in the General Game Playing (GGP) Competition; see Section III] to more modern video games.”
Algorithms for computing strategies in two-player simultaneous move games (2016, unknown): “The success of MCTS was demonstrated by the success of CadiaPlayer which was the top-ranked player of the GGP competition between 2007 and 2009, and also in 2012.”
Computer poker: A review (2011, background): “There are also annual competitions for poker [1], real-time strategy games [19] and general game playing [29].”
The Arcade Learning Environment: An Evaluation Platform for General Agents (Extended Abstract) (2015, background): “The growing interest in competitions such as the General Game Playing competition [Genesereth et al., 2005], Reinforcement Learning competition [Whiteson et al.”
Human-level control through deep reinforcement learning (2015, methodology): “We set out to create a single algorithm that would be able to develop a wide range of competencies on a varied range of challengingtasks—a central goal of general artificial intelligence 13 that has eluded previous efforts 8,14,15 .”