# LESS is More: Rethinking Probabilistic Models of Human Behavior

arXiv: https://arxiv.org/abs/2001.04465 · HTML: https://mlsanity.com/paper/2001.04465/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jan 2020.

## Built on by (most cited first, 17 of 17)

- [Maximum Entropy RL (Provably) Solves Some Robust RL Problems](https://mlsanity.com/paper/2103.06257/) (2021)
- [Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning](https://mlsanity.com/paper/2408.10075/) (2024)
- [Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF](https://mlsanity.com/paper/2312.08358/) (2023)
- [Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased](https://mlsanity.com/paper/2302.01605/) (2023)
- [Efficient Sampling-Based Maximum Entropy Inverse Reinforcement Learning with Application to Autonomous Driving](https://mlsanity.com/paper/2006.13704/) (2020)
- [Modeling the Mistakes of Boundedly Rational Agents Within a Bayesian Theory of Mind](https://mlsanity.com/paper/2106.13249/) (2021)
- [Choice Set Misspecification in Reward Inference](https://mlsanity.com/paper/2101.07691/) (2021)
- [Learning to Make Adherence-Aware Advice](https://mlsanity.com/paper/2310.00817/) (2023)
- [ILoSA: Interactive Learning of Stiffness and Attractors](https://mlsanity.com/paper/2103.03099/) (2021)
- [Pareto-Optimal Learning from Preferences with Hidden Context](https://mlsanity.com/paper/2406.15599/) (2024)
- [Shared Autonomy for Proximal Teaching](https://mlsanity.com/paper/2502.19899/) (2025)
- [Motivating Physical Activity via Competitive Human-Robot Interaction](https://mlsanity.com/paper/2202.07068/) (2022)
- [Dynamically Switching Human Prediction Models for Efficient Planning](https://mlsanity.com/paper/2103.07815/) (2021)
- [A behavioural transformer for effective collaboration between a robot and a non-stationary human](https://mlsanity.com/paper/2307.13447/) (2023)
- [MEReQ: Max-Ent Residual-Q Inverse RL for Sample-Efficient Alignment from Intervention](https://mlsanity.com/paper/2406.16258/) (2024)
- [Aligning Robot Representations with Humans](https://mlsanity.com/paper/2205.07882/) (2022)
- [Corrigible Assistance in One Round: Pragmatic-Pedagogic Best Response](https://mlsanity.com/paper/2607.27508/) (2026)

## Abstract (arXiv)

Robots need models of human behavior for both inferring human goals and preferences, and predicting what people will do. A common model is the Boltzmann noisily-rational decision model, which assumes people approximately optimize a reward function and choose trajectories in proportion to their exponentiated reward. While this model has been successful in a variety of robotics domains, its roots lie in econometrics, and in modeling decisions among different discrete options, each with its own utility or reward. In contrast, human trajectories lie in a continuous space, with continuous-valued features that influence the reward function. We propose that it is time to rethink the Boltzmann model, and design it from the ground up to operate over such trajectory spaces. We introduce a model that explicitly accounts for distances between trajectories, rather than only their rewards. Rather than each trajectory affecting the decision independently, similar trajectories now affect the decision together. We start by showing that our model better explains human behavior in a user study. We then analyze the implications this has for robot inference, first in toy environments where we have ground truth and find more accurate inference, and finally for a 7DOF robot arm learning from user demonstrations.