# Q-based Variational Inverse Reinforcement Learning

arXiv: https://arxiv.org/abs/2608.16888 · HTML: https://mlsanity.com/paper/2608.16888/

## 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.
- Builds on 18 of its 41 references that are in the map.
- First posted on arXiv 17 Aug 2026.

## Placed in

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

## Builds on (most cited first, 18 of 18)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Distributional Reinforcement Learning with Quantile Regression](https://mlsanity.com/paper/1710.10044/) (2017)
- [Implicit Quantile Networks for Distributional Reinforcement Learning](https://mlsanity.com/paper/1806.06923/) (2018)
- [A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress](https://mlsanity.com/paper/1806.06877/) (2018)
- [IQ-Learn: Inverse soft-Q Learning for Imitation](https://mlsanity.com/paper/2106.12142/) (2021)
- [Scalable Bayesian Inverse Reinforcement Learning](https://mlsanity.com/paper/2102.06483/) (2021)
- [Identifiability in inverse reinforcement learning](https://mlsanity.com/paper/2106.03498/) (2021)
- [Model-Based Inverse Reinforcement Learning from Visual Demonstrations](https://mlsanity.com/paper/2010.09034/) (2020)
- [Driving Behavior Modeling using Naturalistic Human Driving Data with Inverse Reinforcement Learning](https://mlsanity.com/paper/2010.03118/) (2020)
- [Invariance in Policy Optimisation and Partial Identifiability in Reward Learning](https://mlsanity.com/paper/2203.07475/) (2022)
- [Driving with Style: Inverse Reinforcement Learning in General-Purpose Planning for Automated Driving](https://mlsanity.com/paper/1905.00229/) (2019)
- [Probabilistic Prediction of Interactive Driving Behavior via Hierarchical Inverse Reinforcement Learning](https://mlsanity.com/paper/1809.02926/) (2018)
- [Risk-Aware Active Inverse Reinforcement Learning](https://mlsanity.com/paper/1901.02161/) (2019)
- [Driving in Real Life with Inverse Reinforcement Learning](https://mlsanity.com/paper/2206.03004/) (2022)
- [Mean-Field Approximation to Gaussian-Softmax Integral with Application to Uncertainty Estimation](https://mlsanity.com/paper/2006.07584/) (2020)
- [Massively Scalable Inverse Reinforcement Learning in Google Maps](https://mlsanity.com/paper/2305.11290/) (2023)
- [Walking the Values in Bayesian Inverse Reinforcement Learning](https://mlsanity.com/paper/2407.10971/) (2024)
- [PAC Apprenticeship Learning with Bayesian Active Inverse Reinforcement Learning](https://mlsanity.com/paper/2508.03693/) (2025)

## Abstract (arXiv)

The development of safe and beneficial AI requires that systems can learn and act in accordance with human preferences. However, explicitly specifying these preferences by hand is often infeasible. Inverse reinforcement learning (IRL) addresses this challenge by inferring preferences, represented as reward functions, from expert behaviour. We introduce Q-based Variational IRL (QVIRL), a novel Bayesian IRL method that recovers a posterior distribution over rewards from expert demonstrations via primarily learning a variational distribution over optimal Q-values. Unlike previous approaches, QVIRL combines scalability with uncertainty quantification, important for safety-critical applications as well as active learning. We demonstrate QVIRL's strong performance in apprenticeship learning across various tasks, including gridworlds, Lunar Lander, the Highway Environment, and two ATARI games both with static expert data and with active learning. It is the first method for Bayesian IRL that demonstrates training from raw pixel observations.