# A Critique of Strictly Batch Imitation Learning

arXiv: https://arxiv.org/abs/2110.02063 · HTML: https://mlsanity.com/paper/2110.02063/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 1 of its 1 references that are in the map.
- First posted on arXiv 5 Oct 2021.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Builds on (most cited first, 1 of 1)

- [Strictly Batch Imitation Learning by Energy-based Distribution Matching](https://mlsanity.com/paper/2006.14154/) (2020)

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

- [OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning](https://mlsanity.com/paper/2405.17477/) (2024)
- [Efficient Imitation under Misspecification](https://mlsanity.com/paper/2503.13162/) (2025)
- [Markov Balance Satisfaction Improves Performance in Strictly Batch Offline Imitation Learning](https://mlsanity.com/paper/2408.09125/) (2024)
- [Conditional Kernel Imitation Learning for Continuous State Environments](https://mlsanity.com/paper/2308.12573/) (2023)

## Abstract (arXiv)

Recent work by Jarrett et al. attempts to frame the problem of offline imitation learning (IL) as one of learning a joint energy-based model, with the hope of out-performing standard behavioral cloning. We suggest that notational issues obscure how the psuedo-state visitation distribution the authors propose to optimize might be disconnected from the policy's textittrue state visitation distribution. We further construct natural examples where the parameter coupling advocated by Jarrett et al. leads to inconsistent estimates of the expert's policy, unlike behavioral cloning.