Including cognitive biases and distance-based rewards in a connectionist model of complex problem solving

Authors:
Frédéric Dandurand;Thomas R. Shultz;Arnaud Rey
Affiliations:
Department of Psychology, Université de Montréal, 90 Vincent-d'Indy Avenue, Montreal, Quebec, H2V 2S9, Canada;Department of Psychology and School of Computer Science, McGill University, 1205 Dr. Penfield Avenue, Montreal, Quebec, H3A 1B1, Canada;Laboratoire de Psychologie Cognitive, CNRS-Aix-Marseille University, 3, place Victor Hugo, 13331 Marseille, France
Venue:
Neural Networks
Year:
2012

Citing 15
Cited 0

Induction: processes of inference, learning, and discovery

Induction: processes of inference, learning, and discovery
Unified theories of cognition

Unified theories of cognition
The cascade-correlation learning architecture

Advances in neural information processing systems 2
Mental leaps: analogy in creative thought

Mental leaps: analogy in creative thought
Temporal difference learning and TD-Gammon

Communications of the ACM
The general counterfeit coin problem

Discrete Mathematics
Learning, action and consciousness: a hybrid approach toward modelling consciousness

Neural Networks - 1997 special issue on neural networks for consciousness
Learning plans without a priori knowledge

Adaptive Behavior
Fundamentals of Neural Network Modeling: Neuropsychology and Cognitive Neuroscience

Fundamentals of Neural Network Modeling: Neuropsychology and Cognitive Neuroscience
Learning Sequences of Compatible Actions Among Agents

Artificial Intelligence Review
Finding minimum entropy codes

Neural Computation
Accelerating autonomous learning by using heuristic selection of actions

Journal of Heuristics
Guiding inference through relational reinforcement learning

ILP'05 Proceedings of the 15th international conference on Inductive Logic Programming
Connectionist Models of Reinforcement, Imitation, and Instruction in Learning to Solve Complex Problems

IEEE Transactions on Autonomous Mental Development
Acquisition of hierarchical reactive skills in a unified cognitive architecture

Cognitive Systems Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.