# Planning with Multiple Biases

## TL;DR

This paper develops a theoretical model to analyze how the interaction of present bias and sunk-cost bias influences decision-making, revealing complex effects and computational challenges in planning with multiple biases.

## Contribution

It introduces a novel model for planning with combined present and sunk-cost biases, including agent awareness levels, and explores their complex interactions and computational implications.

## Key findings

- Biases can mitigate or amplify each other's effects.
- The planning problem is computationally hard for aware agents.
- Natural behavioral phenomena emerge only with both biases present.

## Abstract

Recent work has considered theoretical models for the behavior of agents with specific behavioral biases: rather than making decisions that optimize a given payoff function, the agent behaves inefficiently because its decisions suffer from an underlying bias. These approaches have generally considered an agent who experiences a single behavioral bias, studying the effect of this bias on the outcome. In general, however, decision-making can and will be affected by multiple biases operating at the same time. How do multiple biases interact to produce the overall outcome? Here we consider decisions in the presence of a pair of biases exhibiting an intuitively natural interaction: present bias -- the tendency to value costs incurred in the present too highly -- and sunk-cost bias -- the tendency to incorporate costs experienced in the past into one's plans for the future. We propose a theoretical model for planning with this pair of biases, and we show how certain natural behavioral phenomena can arise in our model only when agents exhibit both biases. As part of our model we differentiate between agents that are aware of their biases (sophisticated) and agents that are unaware of them (naive). Interestingly, we show that the interaction between the two biases is quite complex: in some cases, they mitigate each other's effects while in other cases they might amplify each other. We obtain a number of further results as well, including the fact that the planning problem in our model for an agent experiencing and aware of both biases is computationally hard in general, though tractable under more relaxed assumptions.