Results 1 - 10
of
63
CadiaPlayer: A Simulation-Based General Game Player
- IEEE Trans. Comp. Intell. AI Games
, 2009
"... Abstract—The aim of General Game Playing (GGP) is to create intelligent agents that can automatically learn how to play many different games at an expert level without any human intervention. The traditional design model for GGP agents has been to use a minimax-based game-tree search augmented with ..."
Abstract
-
Cited by 43 (1 self)
- Add to MetaCart
(Show Context)
Abstract—The aim of General Game Playing (GGP) is to create intelligent agents that can automatically learn how to play many different games at an expert level without any human intervention. The traditional design model for GGP agents has been to use a minimax-based game-tree search augmented with an automatically learned heuristic evaluation function. The first successful GGP agents all followed that approach. In here we describe CADIAPLAYER, a GGP agent employing a radically different approach: instead of a traditional game-tree search it uses Monte-Carlo simulations for its move decisions. Furthermore, we empirically evaluate different simulation-based approaches on a wide variety of games; introduce a domain-independent enhancement for automatically learning search-control knowledge to guide the simulation playouts; and show how to adapt the simulation searches to be more effective in single-agent games. CADIAPLAYER has already proven its effectiveness by winning
A general game description language for incomplete information games
- In: Proc. AAAI
, 2010
"... A General Game Player is a system that can play previously unknown games given nothing but their rules. The Game Description Language (GDL) has been developed as a high-level knowledge representation formalism for axiomatising the rules of any game, and a basic requirement of a General Game Player i ..."
Abstract
-
Cited by 31 (17 self)
- Add to MetaCart
(Show Context)
A General Game Player is a system that can play previously unknown games given nothing but their rules. The Game Description Language (GDL) has been developed as a high-level knowledge representation formalism for axiomatising the rules of any game, and a basic requirement of a General Game Player is the ability to reason logically about a given game description. In this paper, we address the fundamen-tal limitation of existing GDL to be confined to deterministic games with complete information about the game state. To this end, we develop an extension of GDL that is both simple and elegant yet expressive enough to allow to formalise the rules of arbitrary (discrete and finite) n-player games with randomness and incomplete state knowledge. We also show that this extension suffices to provide players with all infor-mation they need to reason about their own knowledge as well as that of the other players up front and during game play.
Knowledge generation for improving simulations in UCT for general game playing
- In AI 2008: Advances in Artificial Intelligence
"... Abstract. General Game Playing (GGP) aims at developing game play-ing agents that are able to play a variety of games and, in the absence of pre-programmed game specific knowledge, become proficient players. Most GGP players have used standard tree-search techniques enhanced by automatic heuristic l ..."
Abstract
-
Cited by 21 (3 self)
- Add to MetaCart
(Show Context)
Abstract. General Game Playing (GGP) aims at developing game play-ing agents that are able to play a variety of games and, in the absence of pre-programmed game specific knowledge, become proficient players. Most GGP players have used standard tree-search techniques enhanced by automatic heuristic learning. The UCT algorithm, a simulation-based tree search, is a new approach and has been used successfully in GGP. However, it relies heavily on random simulations to assign values to un-visited nodes and selecting nodes for descending down a tree. This can lead to slower convergence times in UCT. In this paper, we discuss the generation and evolution of domain-independent knowledge using both state and move patterns. This is then used to guide the simulations in UCT. In order to test the improvements, we create matches between a player using standard the UCT algorithm and one using UCT enhanced with knowledge.
M.: A multiagent semantics for the Game Description Language
- In: ICAART
, 2009
"... Abstract. The Game Description Language (GDL) has been developed for the purpose of formalizing game rules. It serves as the input language for general game players, which are systems that learn to play previously unknown games without human intervention. In this paper, we show how GDL descriptions ..."
Abstract
-
Cited by 16 (8 self)
- Add to MetaCart
(Show Context)
Abstract. The Game Description Language (GDL) has been developed for the purpose of formalizing game rules. It serves as the input language for general game players, which are systems that learn to play previously unknown games without human intervention. In this paper, we show how GDL descriptions can be intepreted as multiagent domains and, conversely, how a large class of multiagent environments can be specified in GDL. The resulting specifications are declarative, compact, and easy to understand and maintain. At the same time they can be fully automatically understood and used by autonomous agents who intend to participate in these environments. Our main result is a formal characterization of the class of multiagent domains that serve as formal semantics for—and can be described in—the Game Description Language. 1
As time goes by: Constraint handling rules -- A survey of CHR research between 1998 and 2007
, 2009
"... Constraint Handling Rules (CHR) is a high-level programming language based on multiheaded multiset rewrite rules. Originally designed for writing user-defined constraint solvers, it is now recognized as an elegant general purpose language. CHR-related research has surged during the decade following ..."
Abstract
-
Cited by 16 (11 self)
- Add to MetaCart
Constraint Handling Rules (CHR) is a high-level programming language based on multiheaded multiset rewrite rules. Originally designed for writing user-defined constraint solvers, it is now recognized as an elegant general purpose language. CHR-related research has surged during the decade following the previous survey by Frühwirth (1998). Covering more than 180 publications, this new survey provides an overview of recent results in a wide range of research areas, from semantics and analysis to systems, extensions and applications.
A Parallel General Game Player
"... We have parallelized our general game player Ary on a cluster of computers. We propose multiple par-allelization algorithms. For the sake of simplicity all our algorithms have processes that run independently and that join their results at the end of the thinking time in order to choose a move. Par ..."
Abstract
-
Cited by 16 (3 self)
- Add to MetaCart
We have parallelized our general game player Ary on a cluster of computers. We propose multiple par-allelization algorithms. For the sake of simplicity all our algorithms have processes that run independently and that join their results at the end of the thinking time in order to choose a move. Parallelization works very well for checkers, quite well for other two player sequential move games and not at all for a few other games.
Answer Set Programming for Single-Player Games in General Game Playing
"... Abstract. As a novel, grand AI challenge, General Game Playing is concerned with the development of systems that understand the rules of unknown games and play these games well without human intervention. In this paper, we show how Answer Set Programming can assist a general game player with the spe ..."
Abstract
-
Cited by 14 (5 self)
- Add to MetaCart
(Show Context)
Abstract. As a novel, grand AI challenge, General Game Playing is concerned with the development of systems that understand the rules of unknown games and play these games well without human intervention. In this paper, we show how Answer Set Programming can assist a general game player with the special class of single-player games. To this end, we present a translation from the general Game Description Language (GDL) into answer set programs (ASP). Correctness of this mapping is established by proving that the stable models of the resulting ASP coincide with the possible developments of the original GDL game. We report on experiments with single-player games from past AAAI General Game Playing Competitions which substantiate the claim that Answer Set Programming can provide valuable support to general game playing systems for this type of games. 1
Automated Theorem Proving for General Game Playing
"... A general game player is a system that understands the rules of an unknown game and learns to play this game well without human intervention. To succeed in this endeavor, systems need to be able to extract and prove game-specific knowledge from the mere game rules. We present a practical approach to ..."
Abstract
-
Cited by 12 (10 self)
- Add to MetaCart
A general game player is a system that understands the rules of an unknown game and learns to play this game well without human intervention. To succeed in this endeavor, systems need to be able to extract and prove game-specific knowledge from the mere game rules. We present a practical approach to this challenge with the help of Answer Set Programming. The key idea is to reduce the automated theorem proving task to a simple proof of an induction step and its base case. We prove correctness of this method and report on experiments with an offthe-shelf Answer Set Programming system in combination with a successful general game player. 1
Learning physically-instantiated game play through visual observation
- In Proc. of the IEEE Int.’l Conf. on Robotics and Automation
"... Abstract — We present an integrated vision and robotic sys-tem that plays, and learns to play, simple physically-instantiated board games that are variants of TIC TAC TOE and HEXA-PAWN. We employ novel custom vision and robotic hardware designed specifically for this learning task. The game rules ca ..."
Abstract
-
Cited by 10 (2 self)
- Add to MetaCart
Abstract — We present an integrated vision and robotic sys-tem that plays, and learns to play, simple physically-instantiated board games that are variants of TIC TAC TOE and HEXA-PAWN. We employ novel custom vision and robotic hardware designed specifically for this learning task. The game rules can be parametrically specified. Two independent computational agents alternate playing the two opponents with the shared vi-sion and robotic hardware, using pre-specified rule sets. A third independent computational agent, sharing the same hardware, learns the game rules solely by observing the physical play, without access to the pre-specified rule set, using inductive logic programming with minimal background knowledge possessed by human children. The vision component of our integrated system reliably detects the position of the board in the image and reconstructs the game state after every move, from a single image. The robotic component reliably moves pieces both between board positions and to and from off-board positions as needed by an arbitrary parametrically-specified legal-move generator. Thus the rules of games learned solely by observing physical play can drive further physical play. We demonstrate our system learning to play six different games. I.
The general game playing description language is universal
- In Proceedings of the International Joint Conference on Artificial Intelligence
, 2011
"... The Game Description Language is a high-level, rule-based formalisms for communicating the rules of arbitrary games to general game-playing sys-tems, whose challenging task is to learn to play pre-viously unknown games without human interven-tion. Originally designed for deterministic games with com ..."
Abstract
-
Cited by 9 (6 self)
- Add to MetaCart
The Game Description Language is a high-level, rule-based formalisms for communicating the rules of arbitrary games to general game-playing sys-tems, whose challenging task is to learn to play pre-viously unknown games without human interven-tion. Originally designed for deterministic games with complete information about the game state, the language was recently extended to include ran-domness and imperfect information. However, de-termining the extent to which this enhancement al-lows to describe truly arbitrary games was left as an open problem. We provide a positive answer to this question by relating the extended Game Descrip-tion Language to the universal, mathematical con-cept of extensive-form games, proving that indeed just any such game can be described faithfully.
