Where Do Human Heuristics Come From?

Abstract

Human decision-making deviates from the optimal solution, that maximizes cumulative rewards, in many situations. Here we approach this discrepancy from the perspective of bounded rationality and our goal is to provide a justification for such seemingly sub-optimal strategies. More specifically we investigate the hypothesis, that humans do not know optimal decision-making algorithms in advance, but instead employ a learned, resource-bounded approximation. The idea is formalized through combining a recently proposed meta-learning model based on Recurrent Neural Networks with a resource-bounded objective. The resulting approach is closely connected to variational inference and the Minimum Description Length principle. Empirical evidence is obtained from a two-armed bandit task. Here we observe patterns in our family of models that resemble differences between individual human participants.

Final version for CogSci 2019

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Playing Atari with Deep Reinforcement Learning
• RL${}^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
• Learning to reinforcement learn
• Bayesian Compression for Deep Learning
• Thermodynamics as a theory of decision-making with information processing costs
• A tutorial introduction to the minimum description length principle
• Bayesian Recurrent Neural Networks
• BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems
• Causal Reasoning from Meta-reinforcement Learning