# The Virtues of Pessimism in Inverse Reinforcement Learning

arXiv: https://arxiv.org/abs/2402.02616 · HTML: https://mlsanity.com/paper/2402.02616/

## 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 27 of its 41 references that are in the map.
- First posted on arXiv 4 Feb 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, 27 of 27)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction](https://mlsanity.com/paper/1906.00949/) (2019)
- [AWAC: Accelerating Online Reinforcement Learning with Offline Datasets](https://mlsanity.com/paper/2006.09359/) (2020)
- [IQ-Learn: Inverse soft-Q Learning for Imitation](https://mlsanity.com/paper/2106.12142/) (2021)
- [AlgaeDICE: Policy Gradient from Arbitrary Experience](https://mlsanity.com/paper/1912.02074/) (2019)
- [Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient](https://mlsanity.com/paper/2210.06718/) (2022)
- [GenDICE: Generalized Offline Estimation of Stationary Values](https://mlsanity.com/paper/2002.09072/) (2020)
- [Adversarially Trained Actor Critic for Offline Reinforcement Learning](https://mlsanity.com/paper/2202.02446/) (2022)
- [Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap](https://mlsanity.com/paper/2103.03236/) (2021)
- [GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values](https://mlsanity.com/paper/2001.11113/) (2020)
- [f-IRL: Inverse Reinforcement Learning via State Marginal Matching](https://mlsanity.com/paper/2011.04709/) (2020)
- [Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement](https://mlsanity.com/paper/2002.11089/) (2020)
- [Scalable Bayesian Inverse Reinforcement Learning](https://mlsanity.com/paper/2102.06483/) (2021)
- [Causal Imitation Learning with Unobserved Confounders](https://mlsanity.com/paper/2208.06267/) (2022)
- [Inverse Reinforcement Learning without Reinforcement Learning](https://mlsanity.com/paper/2303.14623/) (2023)
- [Sequence Model Imitation Learning with Unobserved Contexts](https://mlsanity.com/paper/2208.02225/) (2022)
- [SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards](https://mlsanity.com/paper/1905.11108/) (2019)
- [Causal Imitation Learning under Temporally Correlated Noise](https://mlsanity.com/paper/2202.01312/) (2022)
- [Minimax Optimal Online Imitation Learning via Replay Estimation](https://mlsanity.com/paper/2205.15397/) (2022)
- [Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size](https://mlsanity.com/paper/2211.11092/) (2022)
- [CLARE: Conservative Model-Based Reward Learning for Offline Inverse Reinforcement Learning](https://mlsanity.com/paper/2302.04782/) (2023)
- [OPIRL: Sample Efficient Off-Policy Inverse Reinforcement Learning via Distribution Matching](https://mlsanity.com/paper/2109.04307/) (2021)
- [Offline Inverse Reinforcement Learning](https://mlsanity.com/paper/2106.05068/) (2021)

## Abstract (arXiv)

Inverse Reinforcement Learning (IRL) is a powerful framework for learning complex behaviors from expert demonstrations. However, it traditionally requires repeatedly solving a computationally expensive reinforcement learning (RL) problem in its inner loop. It is desirable to reduce the exploration burden by leveraging expert demonstrations in the inner-loop RL. As an example, recent work resets the learner to expert states in order to inform the learner of high-reward expert states. However, such an approach is infeasible in the real world. In this work, we consider an alternative approach to speeding up the RL subroutine in IRL: pessimism, i.e., staying close to the expert's data distribution, instantiated via the use of offline RL algorithms. We formalize a connection between offline RL and IRL, enabling us to use an arbitrary offline RL algorithm to improve the sample efficiency of IRL. We validate our theory experimentally by demonstrating a strong correlation between the efficacy of an offline RL algorithm and how well it works as part of an IRL procedure. By using a strong offline RL algorithm as part of an IRL procedure, we are able to find policies that match expert performance significantly more efficiently than the prior art.