# Inverse reinforcement learning

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

## Key facts

- Inverse reinforcement learning: 321 papers on arXiv since 2018 (data through 7 Oct 2026).
- 40 of its 321 mapped papers (12%) cite “A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress” (2018, arXiv 1806.06877).
- 22 of its 321 mapped papers (7%) cite “Identifiability in inverse reinforcement learning” (2021, arXiv 2106.03498).
- 4 new papers 17 Sep–7 Oct.

## Most cited here

- [A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress](https://mlsanity.com/paper/1806.06877/) (2018), cited by 40 papers here
- [Identifiability in inverse reinforcement learning](https://mlsanity.com/paper/2106.03498/) (2021), cited by 22 papers here
- [Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations](https://mlsanity.com/paper/1904.06387/) (2019), cited by 20 papers here
- [f-IRL: Inverse Reinforcement Learning via State Marginal Matching](https://mlsanity.com/paper/2011.04709/) (2020), cited by 20 papers here
- [Scalable Bayesian Inverse Reinforcement Learning](https://mlsanity.com/paper/2102.06483/) (2021), cited by 19 papers here
- [Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees](https://mlsanity.com/paper/2210.01808/) (2022), cited by 18 papers here
- [Multi-Agent Adversarial Inverse Reinforcement Learning](https://mlsanity.com/paper/1907.13220/) (2019), cited by 17 papers here
- [Meta-Inverse Reinforcement Learning with Probabilistic Context Variables](https://mlsanity.com/paper/1909.09314/) (2019), cited by 16 papers here
- [Adversarial Imitation via Variational Inverse Reinforcement Learning](https://mlsanity.com/paper/1809.06404/) (2018), cited by 14 papers here
- [Learning a Prior over Intent via Meta-Inverse Reinforcement Learning](https://mlsanity.com/paper/1805.12573/) (2018), cited by 12 papers here

## New (17 Sep–7 Oct)

- [Learning Unknown Constraints without Unsafe Data via Optimality and Counterfactual Regularization](https://mlsanity.com/paper/2610.09350/) (2026-10-07)
- [Scalable Multi-Task Inverse Reinforcement Learning](https://mlsanity.com/paper/2610.00758/) (2026-09-30)
- [Loop-Free Inverse Reinforcement Learning via Sequential Value Recovery with Q-Score Matching](https://mlsanity.com/paper/2609.38955/) (2026-09-30)
- [PHIRL: Aligning Learned Rewards with Task Progress for Inverse Reinforcement Learning](https://mlsanity.com/paper/2609.31855/) (2026-09-25)