# Accounting for Human Learning when Inferring Human Preferences

arXiv: https://arxiv.org/abs/2011.05596 · HTML: https://mlsanity.com/paper/2011.05596/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Inverse reinforcement learning, one of 13 directions in Offline RL and imitation learning from data.
- First posted on arXiv 11 Nov 2020.

## Placed in

- Offline RL and imitation learning from data / [Inverse reinforcement learning](https://mlsanity.com/offlinerl/inverse-reinforcement-learning/)

## Abstract (arXiv)

Inverse reinforcement learning (IRL) is a common technique for inferring human preferences from data. Standard IRL techniques tend to assume that the human demonstrator is stationary, that is that their policy π doesn't change over time. In practice, humans interacting with a novel environment or performing well on a novel task will change their demonstrations as they learn more about the environment or task. We investigate the consequences of relaxing this assumption of stationarity, in particular by modelling the human as learning. Surprisingly, we find in some small examples that this can lead to better inference than if the human was stationary. That is, by observing a demonstrator who is themselves learning, a machine can infer more than by observing a demonstrator who is noisily rational. In addition, we find evidence that misspecification can lead to poor inference, suggesting that modelling human learning is important, especially when the human is facing an unfamiliar environment.