# Time-Inconsistent Planning: A Computational Problem in Behavioral Economics

arXiv: https://arxiv.org/abs/1405.1254 · HTML: https://mlsanity.com/paper/1405.1254/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 May 2014.

## Built on by (most cited first, 4 of 4)

- [Best-Response Bayesian Reinforcement Learning with Bayes-adaptive POMDPs for Centaurs](https://mlsanity.com/paper/2204.01160/) (2022)
- [Reinforcement Learning and Inverse Reinforcement Learning with System 1 and System 2](https://mlsanity.com/paper/1811.08549/) (2018)
- [System-2 Recommenders: Disentangling Utility and Engagement in Recommendation Systems via Temporal Point-Processes](https://mlsanity.com/paper/2406.01611/) (2024)
- [On the Utility of Accounting for Human Beliefs about AI Intention in Human-AI Collaboration](https://mlsanity.com/paper/2406.06051/) (2024)

## Abstract (arXiv)

In many settings, people exhibit behavior that is inconsistent across time --- we allocate a block of time to get work done and then procrastinate, or put effort into a project and then later fail to complete it. An active line of research in behavioral economics and related fields has developed and analyzed models for this type of time-inconsistent behavior. Here we propose a graph-theoretic model of tasks and goals, in which dependencies among actions are represented by a directed graph, and a time-inconsistent agent constructs a path through this graph. We first show how instances of this path-finding problem on different input graphs can reconstruct a wide range of qualitative phenomena observed in the literature on time-inconsistency, including procrastination, abandonment of long-range tasks, and the benefits of reduced sets of choices. We then explore a set of analyses that quantify over the set of all graphs; among other results, we find that in any graph, there can be only polynomially many distinct forms of time-inconsistent behavior; and any graph in which a time-inconsistent agent incurs significantly more cost than an optimal agent must contain a large "procrastination" structure as a minor. Finally, we use this graph-theoretic model to explore ways in which tasks can be designed to help motivate agents to reach designated goals.