Running Head: CONNECTIONIST MODEL OF PROBLEM SOLVING
نویسندگان
چکیده
We present a cognitive, connectionist-based model of complex problem solving that integrates cognitive biases and distance-based and environmental rewards under a temporal-difference learning mechanism. The model is tested against experimental data obtained in a well-defined and planning-intensive problem. We show that incorporating cognitive biases (symmetry and simplicity) in a temporal-difference learning rule (SARSA) increases model adequacy – the solution space explored by biased models better fits observed human solutions. While learning from explicit rewards alone is intrinsically slow, adding distance-based rewards, a measure of closeness to goal, to the learning rule significantly accelerates learning. Finally, the model correctly predicts that explicit rewards have little impact on problem solvers’ ability to discover optimal solutions.
منابع مشابه
Learning and Problem Solving with Multilayer Connectionist Systems a Dissertation Presented Abstract Learning and Problem Solving with Multilayer Connectionist Systems
Learning and Problem Solving with Multilayer Connectionist Systems
متن کاملModelling neglect 1 Running head: MODELLING HEMISPHERIC ASYMMETRIES IN NEGLECT Hemispheric asymmetries in cognitive modelling: Connectionist modelling of unilateral visual neglect and neglect dyslexia
متن کامل
Running Head: PERCEIVED PARTNER VIRTUES AND PROBLEM-SOLVING 1 The Virtue of Problem-Solving: Perceived Partner Virtues as Predictors of Problem-Solving Efficacy Running Head: PERCEIVED PARTNER VIRTUES AND PROBLEM-SOLVING
Three studies involving dating relationships and friendships tested the hypothesis that higher perceived partner virtues (or personal strengths enacted in the context of relationships) are related to greater relationship problem-solving efficacy. Studies 1 and 2 showed that higher perceived partner virtues were related to more relationship problem-solving efficacy concurrently and longitudinall...
متن کاملRunning Head: Inter- and intradisciplinary learning in consultations Title: Learning through inter- and intradisciplinary problem solving: using cognitive apprenticeship to analyse doctor-to-doctor consultation
متن کامل
A Hybrid Learning Model of Abductive Reasoning
Multicausal abductive tasks appear to have deliberate and implicit components: people generate and modify explanations using a series of recognizable steps, but these steps appear to be guided by an implicit hypothesis evaluation process. This paper proposes a hybrid symbolic-connectionist learning architecture for multicausal abduction. The architecture tightly integrates a symbolic Soar model...
متن کامل