# Pareto Inverse Reinforcement Learning for Diverse Expert Policy Generation

arXiv: https://arxiv.org/abs/2408.12110 · HTML: https://mlsanity.com/paper/2408.12110/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Inverse reinforcement learning, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 13 of its 18 references that are in the map.
- First posted on arXiv 22 Aug 2024.

## Placed in

- Offline RL and imitation learning from data / [Inverse reinforcement learning](https://mlsanity.com/offlinerl/inverse-reinforcement-learning/)
- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 13 of 13)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Learning Robust Rewards with Adversarial Inverse Reinforcement Learning](https://mlsanity.com/paper/1710.11248/) (2017)
- [Behavior Transformers: Cloning k modes with one stone](https://mlsanity.com/paper/2206.11251/) (2022)
- [Imitating Human Behaviour with Diffusion Models](https://mlsanity.com/paper/2301.10677/) (2023)
- [IQ-Learn: Inverse soft-Q Learning for Imitation](https://mlsanity.com/paper/2106.12142/) (2021)
- [A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation](https://mlsanity.com/paper/1908.08342/) (2019)
- [Quantifying Differences in Reward Functions](https://mlsanity.com/paper/2006.13900/) (2020)
- [Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees](https://mlsanity.com/paper/2210.01808/) (2022)
- [Scaling Pareto-Efficient Decision Making Via Offline Multi-Objective RL](https://mlsanity.com/paper/2305.00567/) (2023)
- [Dynamics-Aware Comparison of Learned Reward Functions](https://mlsanity.com/paper/2201.10081/) (2022)

## Built on by (most cited first, 1 of 1)

- [Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation](https://mlsanity.com/paper/2605.12000/) (2026)

## Abstract (arXiv)

Data-driven offline reinforcement learning and imitation learning approaches have been gaining popularity in addressing sequential decision-making problems. Yet, these approaches rarely consider learning Pareto-optimal policies from a limited pool of expert datasets. This becomes particularly marked due to practical limitations in obtaining comprehensive datasets for all preferences, where multiple conflicting objectives exist and each expert might hold a unique optimization preference for these objectives. In this paper, we adapt inverse reinforcement learning (IRL) by using reward distance estimates for regularizing the discriminator. This enables progressive generation of a set of policies that accommodate diverse preferences on the multiple objectives, while using only two distinct datasets, each associated with a different expert preference. In doing so, we present a Pareto IRL framework (ParIRL) that establishes a Pareto policy set from these limited datasets. In the framework, the Pareto policy set is then distilled into a single, preference-conditioned diffusion model, thus allowing users to immediately specify which expert's patterns they prefer. Through experiments, we show that ParIRL outperforms other IRL algorithms for various multi-objective control tasks, achieving the dense approximation of the Pareto frontier. We also demonstrate the applicability of ParIRL with autonomous driving in CARLA.