The History Heuristic and Alpha-Beta Search Enhancements in Practice
IEEE Transactions on Pattern Analysis and Machine Intelligence
Finite-time Analysis of the Multiarmed Bandit Problem
Machine Learning
Enhanced Iterative-Deepening Search
IEEE Transactions on Pattern Analysis and Machine Intelligence
Combining online and offline knowledge in UCT
Proceedings of the 24th international conference on Machine learning
Automatic heuristic construction in a complete general game player
AAAI'06 proceedings of the 21st national conference on Artificial intelligence - Volume 2
Heuristic evaluation functions for general game playing
AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 2
Fluxplayer: a successful general game player
AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 2
General game learning using knowledge transfer
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Efficient selectivity and backup operators in Monte-Carlo tree search
CG'06 Proceedings of the 5th international conference on Computers and games
Bandit based monte-carlo planning
ECML'06 Proceedings of the 17th European conference on Machine Learning
Symbolic Classification of General Two-Player Games
KI '08 Proceedings of the 31st annual German conference on Advances in Artificial Intelligence
Knowledge Generation for Improving Simulations in UCT for General Game Playing
AI '08 Proceedings of the 21st Australasian Joint Conference on Artificial Intelligence: Advances in Artificial Intelligence
General Game Playing with Ants
SEAL '08 Proceedings of the 7th International Conference on Simulated Evolution and Learning
Monte-Carlo simulation balancing
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Symbolic Classification of General Multi-Player Games
Proceedings of the 2008 conference on ECAI 2008: 18th European Conference on Artificial Intelligence
Answer Set Programming for Single-Player Games in General Game Playing
ICLP '09 Proceedings of the 25th International Conference on Logic Programming
Neural Networks for State Evaluation in General Game Playing
ECML PKDD '09 Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases: Part II
Automated theorem proving for general game playing
IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
Monte-Carlo exploration for deterministic planning
IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
Coevolving intelligent game players in a cultural framework
CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
Decomposition of Multi-player Games
AI '09 Proceedings of the 22nd Australasian Joint Conference on Advances in Artificial Intelligence
Monte Carlo search applied to card selection in magic: the gathering
CIG'09 Proceedings of the 5th international conference on Computational Intelligence and Games
Nested Monte-Carlo Expression Discovery
Proceedings of the 2010 conference on ECAI 2010: 19th European Conference on Artificial Intelligence
CI in general game playing: to date achievements and perspectives
ICAISC'10 Proceedings of the 10th international conference on Artifical intelligence and soft computing: Part II
Instantiating general games using prolog or dependency graphs
KI'10 Proceedings of the 33rd annual German conference on Advances in artificial intelligence
Computational experiments with the RAVE heuristic
CG'10 Proceedings of the 7th international conference on Computers and games
Score bounded Monte-Carlo tree search
CG'10 Proceedings of the 7th international conference on Computers and games
Monte-Carlo tree search and rapid action value estimation in computer Go
Artificial Intelligence
Translating general game descriptions into an action language
Logic programming, knowledge representation, and nonmonotonic reasoning
A Monte-Carlo AIXI approximation
Journal of Artificial Intelligence Research
The Journal of Machine Learning Research
Multigame playing by means of UCT enhanced with automatically generated evaluation functions
AGI'11 Proceedings of the 4th international conference on Artificial general intelligence
Multi-armed bandits with episode context
Annals of Mathematics and Artificial Intelligence
The grand challenge of computer Go: Monte Carlo tree search and extensions
Communications of the ACM
Evaluation function based monte-carlo LOA
ACG'09 Proceedings of the 12th international conference on Advances in Computer Games
A study of UCT and its enhancements in an artificial game
ACG'09 Proceedings of the 12th international conference on Advances in Computer Games
Continuous upper confidence trees
LION'05 Proceedings of the 5th international conference on Learning and Intelligent Optimization
Real-time solving of quantified CSPs based on Monte-Carlo game tree search
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume One
Guiding combinatorial optimization with UCT
CPAIOR'12 Proceedings of the 9th international conference on Integration of AI and OR Techniques in Constraint Programming for Combinatorial Optimization Problems
Playing repeated Stackelberg games with unknown opponents
Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems - Volume 2
Bootstrapping monte carlo tree search with an imperfect heuristic
ECML PKDD'12 Proceedings of the 2012 European conference on Machine Learning and Knowledge Discovery in Databases - Volume Part II
Searching with partial belief states in general games with incomplete information
KI'12 Proceedings of the 35th Annual German conference on Advances in Artificial Intelligence
Sufficiency-based selection strategy for MCTS
IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
Hi-index | 0.02 |
The aim of General Game Playing (GGP) is to create intelligent agents that automatically learn how to play many different games at an expert level without any human intervention. The most successful GGP agents in the past have used traditional game-tree search combined with an automatically learned heuristic function for evaluating game states. In this paper we describe a GGP agent that instead uses a Monte Carlo/UCT simulation technique for action selection, an approach recently popularized in computer Go. Our GGP agent has proven its effectiveness by winning last year s AAAI GGP Competition. Furthermore, we introduce and empirically evaluate a new scheme for automatically learning search-control knowledge for guiding the simulation playouts, showing that it offers significant benefits for a variety of games.