Methods for Competitive Co-Evolution: Finding Opponents Worth Beating

By Christopher D. Rosin, Richard K. Belew. 1995

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

Emergent Tool Use From Multi-Agent Autocurricula (2019, background): “Early work explored self-play using genetic algorithms [16, 17, 18, 19].”
Evolving Soccer Keepaway Players Through Task Decomposition (2005, background): “At one extreme of this dimension lies the paradigm known as coevolution (Rosin and Belew, 1995; Potter and Jong, 2000; Ficici and Pollack, 1998; Stanley and Miikkulainen, 2004), in which no additional information is given to the learner beyond the task decomposition itself.”
Evolving Keepaway Soccer Players through Task Decomposition (2003, background): “In general, coevolution can be competitive [5,10], in which case the components are adversaries and one component’s gain is another’s loss.”
Cooperative Coevolution: An Architecture for Evolving Coadapted Subcomponents (2000, methodology): “A two-species model has also been used to solve a number of game learning problems, including tic-tac-toe, nim, and go, by having the species represent competing players (Rosin and Belew 1995).”
New Methods for Competitive Coevolution (1997, background): “For example, in anearly set of experiments on 2-dimensional Tic-Tac-Toe, random sampling of opponents was found to requirefewer generations to solve the game than full crossbar testing (Rosin & Belew, 1995).”
Why did TD-Gammon Work? (1996, background): “Rosin & Belew applied competitive fitness to several games (Rosin and Belew, 1995).”
Coevolution of a Backgammon Player (1996, background): “Rosin & Belew applied competitive fitness to several games ( Rosin and Belew, 1995 ).”
The road to everywhere : Evolution, complexity and progress in natural and artificial systems (2008, background): “New parasite types should serve as a drive towards further innovation, creating ever-greater levels of complexity and performance by forcing hosts to respond to a wider range of more challenging parasite test cases (Rosin and Belew [151]).”
Multiagent Systems: A Survey from a Machine Learning Perspective (2000, methodology): “Nevertheless, Rosin and Belew use this technique, along with an interesting method for mainta ining diversity in genetic populations, to evolve agents that can play TicTacToe, Nim, and a simple version of G o [66].”
Genetic and Evolutionary Computation – GECCO 2004 (2004, methodology): “This problem arises in various areas such as facility layout [9], graph partitioning [10], quorum cast routing [5], telecommunications [11], and matrix decomposition [4].”