Exploring NK Fitness Landscapes Using Imitative Learning

Abstract

The idea that a group of cooperating agents can solve problems more efficiently than when those agents work independently is hardly controversial, despite our obliviousness of the conditions that make cooperation a successful problem solving strategy. Here we investigate the performance of a group of agents in locating the global maxima of NK fitness landscapes with varying degrees of ruggedness. Cooperation is taken into account through imitative learning and the broadcasting of messages informing on the fitness of each agent. We find a trade-off between the group size and the frequency of imitation: for rugged landscapes, too much imitation or too large a group yield a performance poorer than that of independent agents. By decreasing the diversity of the group, imitative learning may lead to duplication of work and hence to a decrease of its effective size. However, when the parameters are set to optimal values the cooperative group substantially outperforms the independent agents.

References in corpus (5)

• Degree mixing in multilayer networks impedes the evolution of cooperation
• Imitative learning as a connector of collective brains
• Evolutionary dynamics on rugged fitness landscapes: exact dynamics and information theoretical aspects
• Social interaction as a heuristic for combinatorial optimization problems
• Revisiting the effect of external fields in Axelrod's model of social dynamics

Cited by in corpus (13)

• Agent-based models of collective intelligence
• Influence of network topology on cooperative problem-solving systems
• Mobility helps problem-solving systems to avoid Groupthink
• Effect of group organization on the performance of cooperative processes
• Impact of centrality on cooperative processes
• When more of the same is better
• Awareness improves problem-solving performance
• Reputation blackboard systems
• Policies for allocation of information in task-oriented groups: elitism and egalitarianism outperform welfarism
• The surprising little effectiveness of cooperative algorithms in parallel problem solving
• Predictability of the imitative learning trajectories
• Individual decision making in task-oriented groups
• New Coevolution Dynamic as an Optimization Strategy in Group Problem Solving