# Inverse Reinforcement Learning with Sub-optimal Experts

arXiv: https://arxiv.org/abs/2401.03857 · HTML: https://mlsanity.com/paper/2401.03857/

## Key facts

- Cited by 4 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 11 of its 30 references that are in the map.
- First posted on arXiv 8 Jan 2024.

## Placed in

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

## Builds on (most cited first, 11 of 11)

- [A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress](https://mlsanity.com/paper/1806.06877/) (2018)
- [Invariance in Policy Optimisation and Partial Identifiability in Reward Learning](https://mlsanity.com/paper/2203.07475/) (2022)
- [Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees](https://mlsanity.com/paper/2210.01808/) (2022)
- [Planning in Markov Decision Processes with Gap-Dependent Sample Complexity](https://mlsanity.com/paper/2006.05879/) (2020)
- [Repeated Inverse Reinforcement Learning](https://mlsanity.com/paper/1705.05427/) (2017)
- [AC-Teach: A Bayesian Actor-Critic Method for Policy Learning with an Ensemble of Suboptimal Teachers](https://mlsanity.com/paper/1909.04121/) (2019)
- [Active Exploration for Inverse Reinforcement Learning](https://mlsanity.com/paper/2207.08645/) (2022)
- [Reinforcement Learning from Imperfect Demonstrations under Soft Expert Guidance](https://mlsanity.com/paper/1911.07109/) (2019)
- [Towards Resolving Unidentifiability in Inverse Reinforcement Learning](https://mlsanity.com/paper/1601.06569/) (2016)
- [Identifiability and generalizability from multiple experts in Inverse Reinforcement Learning](https://mlsanity.com/paper/2209.10974/) (2022)
- [Active Policy Improvement from Multiple Black-box Oracles](https://mlsanity.com/paper/2306.10259/) (2023)

## Built on by (most cited first, 4 of 4)

- [VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training](https://mlsanity.com/paper/2508.03058/) (2025)
- [Efficient Imitation under Misspecification](https://mlsanity.com/paper/2503.13162/) (2025)
- [Generalizing Behavior via Inverse Reinforcement Learning with Closed-Form Reward Centroids](https://mlsanity.com/paper/2509.12010/) (2025)
- [Quantifying Potential Observation Missingness in Inverse Reinforcement Learning](https://mlsanity.com/paper/2605.12831/) (2026)

## Abstract (arXiv)

Inverse Reinforcement Learning (IRL) techniques deal with the problem of deducing a reward function that explains the behavior of an expert agent who is assumed to act optimally in an underlying unknown task. In several problems of interest, however, it is possible to observe the behavior of multiple experts with different degree of optimality (e.g., racing drivers whose skills ranges from amateurs to professionals). For this reason, in this work, we extend the IRL formulation to problems where, in addition to demonstrations from the optimal agent, we can observe the behavior of multiple sub-optimal experts. Given this problem, we first study the theoretical properties of the class of reward functions that are compatible with a given set of experts, i.e., the feasible reward set. Our results show that the presence of multiple sub-optimal experts can significantly shrink the set of compatible rewards. Furthermore, we study the statistical complexity of estimating the feasible reward set with a generative model. To this end, we analyze a uniform sampling algorithm that results in being minimax optimal whenever the sub-optimal experts' performance level is sufficiently close to the one of the optimal agent.