Matching Behavior as a Tradeoff Between Reward Maximization and Demands on Neural Computation

Entropy-based metrics for predicting choice behavior based on local response to reward

For decades, behavioral scientists have used the matching law to quantify how animals distribute their choices between multiple options in response to reinforcement they receive. More recently, many reinforcement learning (RL) models have been developed to explain choice by integrating reward feedback over time. Despite reasonable success of RL models in capturing choice on a trial-by-trial basis, these models cannot capture variability in matching behavior. To address this, we developed metrics based on information theory and applied them to choice data from dynamic learning tasks in mice and monkeys. We found that a single entropy-based metric can explain 50% and 41% of variance in matching in mice and monkeys, respectively. We then used limitations of existing RL models in capturing entropy-based metrics to construct more accurate models of choice. Together, our entropy-based metrics provide a model-free tool to predict adaptive choice behavior and reveal underlying neural mechanisms.

Reward Size Informs Repeat-Switch Decisions and Strongly Modulates the Activity of Neurons in Parietal Cortex

Behavior is guided by previous experience. Good, positive outcomes drive a repetition of a previous behavior or choice, whereas poor or bad outcomes lead to an avoidance. How these basic drives are implemented by the brain has been of primary interest to psychology and neuroscience. We engaged animals in a choice task in which the size of a reward outcome strongly governed the animals' subsequent decision whether to repeat or switch the previous choice. We recorded the discharge activity of neurons implicated in reward-based choice in 2 regions of parietal cortex. We found that the tendency to retain previous choice following a large (small) reward was paralleled by a marked decrease (increase) in the activity of parietal neurons. This neural effect is independent of, and of sign opposite to, value-based modulations reported in parietal cortex previously. This effect shares the same basic properties with signals previously reported in the limbic system that detect the size of the recently obtained reward to mediate proper repeat-switch decisions. We conclude that the size of the obtained reward is a decision variable that guides the decision between retaining a choice or switching, and neurons in parietal cortex strongly respond to this novel decision variable.

Optimal decision making and matching are tied through diminishing returns

How individuals make decisions has been a matter of long-standing debate among economists and researchers in the life sciences. In economics, subjects are viewed as optimal decision makers who maximize their overall reward income. This framework has been widely influential, but requires a complete knowledge of the reward contingencies associated with a given choice situation. Psychologists and ecologists have observed that individuals tend to use a simpler "matching" strategy, distributing their behavior in proportion to relative rewards associated with their options. This article demonstrates that the two dominant frameworks of choice behavior are linked through the law of diminishing returns. The relatively simple matching can in fact provide maximal reward when the rewards associated with decision makers' options saturate with the invested effort. Such saturating relationships between reward and effort are hallmarks of the law of diminishing returns. Given the prevalence of diminishing returns in nature and social settings, this finding can explain why humans and animals so commonly behave according to the matching law. The article underscores the importance of the law of diminishing returns in choice behavior.

Matching Behavior as a Tradeoff Between Reward Maximization and Demands on Neural Computation

When faced with a choice, humans and animals commonly distribute their behavior in proportion to the frequency of payoff of each option. Such behavior is referred to as matching and has been captured by the matching law. However, matching is not a general law of economic choice. Matching in its strict sense seems to be specifically observed in tasks whose properties make matching an optimal or a near-optimal strategy. We engaged monkeys in a foraging task in which matching was not the optimal strategy. Over-matching the proportions of the mean offered reward magnitudes would yield more reward than matching, yet, surprisingly, the animals almost exactly matched them. To gain insight into this phenomenon, we modeled the animals' decision-making using a mechanistic model. The model accounted for the animals' macroscopic and microscopic choice behavior. When the models' three parameters were not constrained to mimic the monkeys' behavior, the model over-matched the reward proportions and in doing so, harvested substantially more reward than the monkeys. This optimized model revealed a marked bottleneck in the monkeys' choice function that compares the value of the two options. The model featured a very steep value comparison function relative to that of the monkeys. The steepness of the value comparison function had a profound effect on the earned reward and on the level of matching. We implemented this value comparison function through responses of simulated biological neurons. We found that due to the presence of neural noise, steepening the value comparison requires an exponential increase in the number of value-coding neurons. Matching may be a compromise between harvesting satisfactory reward and the high demands placed by neural noise on optimal neural computation.