55,282 Hits in 6.6 sec

Neuro-evolution versus Particle Swarm Optimization for competitive co-evolution of pursuit-evasion behaviors

Leo. H. Langenhoven, Geoff. S. Nitschke
2010 IEEE Congress on Evolutionary Computation  
This task requires one predator agent to capture one prey agent in a simulation where behavior adaptation is guided by an arms race of competitive coevolution.  ...  This paper presents a study that compares the efficacy of Neuro-Evolution (NE) versus Particle Swarm Optimization (PSO) for evolving Artificial Neural Network (ANN) controllers in an unsupervised adaptation  ...  Various approaches to agent behavior adaptation in pursuit-evasion tasks have been studied within a competitive co-evolution context.  ... 
doi:10.1109/cec.2010.5585971 dblp:conf/cec/LangenhovenN10 fatcat:creqsdqg7bejnay6wnqissfyf4

Orthogonally Evolved AI to Improve Difficulty Adjustment in Video Games [chapter]

Arend Hintze, Randal S. Olson, Joel Lehman
2016 Lecture Notes in Computer Science  
In this publication we test a new approach for difficulty adjustment in games: orthogonally evolved AI, where the player receives support from collaborating agents that are co-evolved with opponent agents  ...  In games where the player interacts with computer-controlled opponents, the difficulty of the game can be adjusted not only by changing the distribution of opponents or game resources, but also through  ...  In one, the player is immersed in a world where the computer-controlled game agents evolve in real-time as the game is played.  ... 
doi:10.1007/978-3-319-31204-0_34 fatcat:2npt2kmnbnfkhaek4i6o23li5e

Towards more intelligent adaptive video game agents

Simon M. Lucas, Philipp Rohlfshagen, Diego Perez
2012 Proceedings of the 9th conference on Computing Frontiers - CF '12  
Strengths and weaknesses of each approach are identified, and some research directions are outlined that may soon lead to significantly improved video game agents with lower development costs.  ...  This paper provides a computational intelligence perspective on the design of intelligent video game agents.  ...  For example, if intransitivities are suspected as being the main problem in co-evolving a game agent, then the same experimental setup can be used with the exception of replacing the relative (co-evolutionary  ... 
doi:10.1145/2212908.2212955 dblp:conf/cf/LucasRP12 fatcat:rtgibipfrnaabox44jla5a4sam

Evolutionary Learning of Multiagents Using Strategic Coalition in the IPD Game [chapter]

Seung-Ryong Yang, Sung-Bae Cho
2003 Lecture Notes in Computer Science  
We propose strategic coalition consisting of many agents and simulate their emergence in a co-evolutionary learning environment.  ...  In this paper, we use the Iterated Prisoner's Dilemma (IPD) game, which is a simple model to deal with complex problems for dynamic systems.  ...  In other words, players in the population also gradually evolve to adapt to their environment.  ... 
doi:10.1007/978-3-540-39896-7_5 fatcat:zfg3sqjrtrf77phq5y6gf4uvqu

Adaptive cyclically dominating game on co-evolving networks: Numerical and analytic results [article]

Chi Wun Choi, Chen Xu, Pak Ming Hui
2016 arXiv   pre-print
A co-evolving and adaptive Rock (R)-Paper (P)-Scissors (S) game (ARPS) in which an agent uses one of three cyclically dominating strategies is proposed and studied numerically and analytically.  ...  A mean-field theory of link densities in co-evolving network is formulated in a general way that can be readily modified to other co-evolving network problems of multiple strategies.  ...  In particular, the present work is motivated by the two-option adaptive co-evolving voter model [22] and the dissatisfied adaptive snowdrift game [20, 23] .  ... 
arXiv:1605.03370v1 fatcat:pukk5cppizcjjigqywphmeq5za

Co-evolutionary learning with strategic coalition for multiagents

Seung-Ryong Yang, Sung-Bae Cho
2005 Applied Soft Computing  
adaptive agents and simulate its emergence in a co-evolutionary learning environment.  ...  Experimental results show that co-evolutionary learning with coalition and confidence can produce better performing agents that generalize well against unseen agents. #  ...  game with co-evolutionary learning process.  ... 
doi:10.1016/j.asoc.2004.07.002 fatcat:5lmuuamdcjetjgyt5scg6vtpu4

Evolutionary computation and games

S.M. Lucas, G. Kendall
2006 IEEE Computational Intelligence Magazine  
Within the evolutionary computation (EC) literature, this is known as co-evolution and within this paradigm, expert game-playing strategies have been evolved without the need for human expertise.  ...  The "Evolving Game Strategies" sidebar discusses the main design decisions involved when applying evolution in this way.  ...  The first conference (co-chaired by the authors) took place in April 2005 and led to this article.  ... 
doi:10.1109/mci.2006.1597057 fatcat:6o7yidxnirftvarbpx2fcxqh44


Akira Namatame, Naoto Sato, Kazuyuki Murakami
2004 Recent Advances in Simulated Evolution and Learning  
This paper also presents a comparative study of two evolving populations, one in a spatial environment, and the other in a small-world environment.  ...  This question will depend crucially on how self-interested agents interact and how they learn from each other. We model strategic interactions as dilemma games, coordination games or hawk-dove games.  ...  While the concept and techniques of game theory have been used extensively in many diverse contexts, they have been unsuccessful in explaining how agents realize if a game has many equilibria 8 .  ... 
doi:10.1142/9789812561794_0001 dblp:conf/seal/NamatameSM02 fatcat:6ql7zb23gbbkxkuzlqxtpuw7gy

Automated mechanism design with co-evolutionary hierarchical genetic programming techniques

John A. Doucette, Darren Abramson
2012 Proceedings of the fourteenth international conference on Genetic and evolutionary computation conference - GECCO '12  
We present a novel form of automated game theoretic mechanism design in which mechanisms and players co-evolve.  ...  The resulting model is evaluated by evolving mechanisms for the ultimatum game, and replicates the results of empirical studies of human economic behaviors, as well as demonstrating the ability to evaluate  ...  For example, a population of trading agents may co-evolve with a population of mechanisms [14] .  ... 
doi:10.1145/2330163.2330293 dblp:conf/gecco/DoucetteA12 fatcat:pqun6v6sf5g4dd47nbj63hrjke

Cycling Co-Evolution Resulting from Genetic Adaptation in Two-Person Zero-Sum Games

David Salamon, Peter Salamon
2005 Open systems & information dynamics  
We consider two populations co-evolving with fitness defined by the payoff in a twoperson zero-sum game.  ...  We show that such situations lead to spontaneous and sustained oscillations iff the optimal strategy of the game is mixed.  ...  Palacios, and the participants in the SDSU mathematical biology seminar for helpful discussions.  ... 
doi:10.1007/s11080-005-0924-1 fatcat:3s7zt2xhsfcathb5e7pcqa6bmi

Replicator Dynamics of Co-Evolving Networks [article]

Aram Galstyan, Ardeshir Kianercy, Armen Allahverdyan
2011 arXiv   pre-print
We propose a simple model of network co-evolution in a game-dynamical system of interacting agents that play repeated games with their neighbors, and adapt their behaviors and network links based on the  ...  In particular, we suggest an appropriate factorization of the agents' strategies that results in a coupled system of equations characterizing the evolution of both strategies and network structure, and  ...  Dynamics for Co-Evolving Networks Let us consider a set of agents that play repeated games with each other.  ... 
arXiv:1107.5354v1 fatcat:s4b2rejapjdj7l6zzr6hdeuxc4

From competition to cooperation: Co-evolution in a rewards continuum

Daniel Ashlock, Wendy Ashlock, Spyridon Samothrakis, Simon Lucas, Colin Lee
2012 2012 IEEE Conference on Computational Intelligence and Games (CIG)  
The games are compared by examining the way use of moves evolves, by using transitivity measures on evolved agents, by estimating the complexity of the agents and by checking for non-local adaptation.  ...  Many of the measurements used to compare different games are found to exhibit a nonlinear responses to the change in payoff matrix.  ...  Nonlocal Adaptation Informally, nonlocal adaptation (NLA) is the degree to which additional evolution of a population of co-evolving agents improves their competitive ability.  ... 
doi:10.1109/cig.2012.6374135 dblp:conf/cig/AshlockASLL12 fatcat:ceqqafgxvfhkbivoo4g4j2wqoy

Pareto Evolution and Co-Evolution in Cognitive Neural Agents Synthesis for Tic-Tac-Toe

Yi Jack Yau, Jason Teo, Patricia Anthony
2007 2007 IEEE Symposium on Computational Intelligence and Games  
The results indicate that the canonical PEP system outperformed both co-evolutionary PEP systems as it was able to evolve ANN agents with higher quality game-playing performance as both first and second  ...  Three systems are compared: (i) a canonical PEP system, (ii) a co-evolving PEP system (PCEP) with 3 different setups, and (iii) a co-evolving PEP system that uses an archive (PCEP-A) with 3 different setups  ...  In particular, we wish to thank J.Y. Luke, H. Kauthary and W.K Ng for their time and assistance. We are also grateful to the anonymous reviewers for their helpful comments.  ... 
doi:10.1109/cig.2007.368113 dblp:conf/cig/YauTA07 fatcat:yy3645vkk5adrasot3opwqttf4

Towards adaptive online RTS AI with NEAT

Jason M. Traish, James R. Tulip
2012 2012 IEEE Conference on Computational Intelligence and Games (CIG)  
The results of the experiments show that NEAT can produce satisfactory RTS agents, and can also create agents capable of displaying complex in-game adaptive behavior.  ...  M Traish is with the School  ...  Experiment 4 demonstrated that NEAT was capable of generating agents with complex in-game adaptive behaviors.  ... 
doi:10.1109/cig.2012.6374187 dblp:conf/cig/TraishT12 fatcat:qzeextjlrrektkomglhiholzby

Evolution of cartesian genetic programs capable of learning

Gul Muhammad Khan, Julian F. Miller
2009 Proceedings of the 11th Annual conference on Genetic and evolutionary computation - GECCO '09  
Also, co-evolved agents show significantly increased learning capabilities compared to those that were evolved to play against a minimax-based opponent.  ...  Secondly, we show that we can obtain learning programs much quicker through co-evolution in comparison to the evolution of agents against a minimax based checkers program.  ...  In second case we have co-evolved agents against each other allowing both agents to develop over five game series.  ... 
doi:10.1145/1569901.1569999 dblp:conf/gecco/KhanM09 fatcat:6ztuzgqahjagdgpe7fnu5so7de
« Previous Showing results 1 — 15 out of 55,282 results