# When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?

arXiv: https://arxiv.org/abs/2204.05618 · HTML: https://mlsanity.com/paper/2204.05618/

## Key facts

- Cited by 89 papers in the map (data through 14 Oct 2026).
- Placed in Offline RL algorithms, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 60 of its 74 references that are in the map.
- First posted on arXiv 12 Apr 2022.

## Placed in

- Offline RL and imitation learning from data / [Offline RL algorithms](https://mlsanity.com/offlinerl/offline-rl-algorithms/)

## Builds on (most cited first, 30 of 60)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [Off-Policy Deep Reinforcement Learning without Exploration](https://mlsanity.com/paper/1812.02900/) (2018)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures](https://mlsanity.com/paper/1802.01561/) (2018)
- [Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction](https://mlsanity.com/paper/1906.00949/) (2019)
- [Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning](https://mlsanity.com/paper/1910.00177/) (2019)
- [QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation](https://mlsanity.com/paper/1806.10293/) (2018)
- [What Matters in Learning from Offline Human Demonstrations for Robot Manipulation](https://mlsanity.com/paper/2108.03298/) (2021)
- [Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations](https://mlsanity.com/paper/1709.10087/) (2017)
- [AWAC: Accelerating Online Reinforcement Learning with Offline Datasets](https://mlsanity.com/paper/2006.09359/) (2020)
- [Behavior Regularized Offline Reinforcement Learning](https://mlsanity.com/paper/1911.11361/) (2019)
- [MOPO: Model-based Offline Policy Optimization](https://mlsanity.com/paper/2005.13239/) (2020)
- [MOReL : Model-Based Offline Reinforcement Learning](https://mlsanity.com/paper/2005.05951/) (2020)
- [Implicit Behavioral Cloning](https://mlsanity.com/paper/2109.00137/) (2021)
- [COMBO: Conservative Offline Model-Based Policy Optimization](https://mlsanity.com/paper/2102.08363/) (2021)
- [Is Pessimism Provably Efficient for Offline RL?](https://mlsanity.com/paper/2012.15085/) (2020)
- [Information-Theoretic Considerations in Batch Reinforcement Learning](https://mlsanity.com/paper/1905.00360/) (2019)
- [Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism](https://mlsanity.com/paper/2103.12021/) (2021)
- [Critic Regularized Regression](https://mlsanity.com/paper/2006.15134/) (2020)
- [Bellman-consistent Pessimism for Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06926/) (2021)
- [Offline Reinforcement Learning with Fisher Divergence Critic Regularization](https://mlsanity.com/paper/2103.08050/) (2021)
- [MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale](https://mlsanity.com/paper/2104.08212/) (2021)

## Built on by (most cited first, 30 of 89)

- [VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training](https://mlsanity.com/paper/2210.00030/) (2022)
- [RoboCLIP: One Demonstration is Enough to Learn Robot Policies](https://mlsanity.com/paper/2310.07899/) (2023)
- [Large Language Models for Robotics: A Survey](https://mlsanity.com/paper/2311.07226/) (2023)
- [Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions](https://mlsanity.com/paper/2309.10150/) (2023)
- [Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization](https://mlsanity.com/paper/2303.15810/) (2023)
- [Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deployment](https://mlsanity.com/paper/2211.08416/) (2022)
- [Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL](https://mlsanity.com/paper/2209.03993/) (2022)
- [RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold](https://mlsanity.com/paper/2406.14532/) (2024)
- [Self-Adapting Language Models](https://mlsanity.com/paper/2506.10943/) (2025)
- [Offline Reinforcement Learning for LLM Multi-Step Reasoning](https://mlsanity.com/paper/2412.16145/) (2024)
- [Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations](https://mlsanity.com/paper/2311.05584/) (2023)
- [CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding](https://mlsanity.com/paper/2506.13725/) (2025)
- [MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action Models](https://mlsanity.com/paper/2503.08007/) (2025)
- [Context-Aware Language Modeling for Goal-Oriented Dialogue Systems](https://mlsanity.com/paper/2204.10198/) (2022)
- [Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets](https://mlsanity.com/paper/2306.14069/) (2023)
- [Self-Recognition in Language Models](https://mlsanity.com/paper/2407.06946/) (2024)
- [Real World Offline Reinforcement Learning with Realistic Data Source](https://mlsanity.com/paper/2210.06479/) (2022)
- [Embedding Synthetic Off-Policy Experience for Autonomous Driving via Zero-Shot Curricula](https://mlsanity.com/paper/2212.01375/) (2022)
- [Distributionally Robust Model-based Reinforcement Learning with Large State Spaces](https://mlsanity.com/paper/2309.02236/) (2023)
- [Model-based Trajectory Stitching for Improved Offline Reinforcement Learning](https://mlsanity.com/paper/2211.11603/) (2022)
- [Hierarchical Imitation Learning with Vector Quantized Models](https://mlsanity.com/paper/2301.12962/) (2023)
- [Learning to Discern: Imitating Heterogeneous Human Demonstrations with Preference and Representation Learning](https://mlsanity.com/paper/2310.14196/) (2023)
- [Guided Online Distillation: Promoting Safe Reinforcement Learning by Offline Demonstration](https://mlsanity.com/paper/2309.09408/) (2023)
- [VerifierQ: Enhancing LLM Test Time Compute with Q-Learning-based Verifiers](https://mlsanity.com/paper/2410.08048/) (2024)
- [Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning](https://mlsanity.com/paper/2310.19308/) (2023)
- [EXTRACT: Efficient Policy Learning by Extracting Transferable Robot Skills from Offline Data](https://mlsanity.com/paper/2406.17768/) (2024)
- [Offline Reinforcement Learning for Wireless Network Optimization with Mixture Datasets](https://mlsanity.com/paper/2311.11423/) (2023)
- [Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL](https://mlsanity.com/paper/2505.18098/) (2025)
- [Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning](https://mlsanity.com/paper/2411.05193/) (2024)
- [Yes, Q-learning Helps Offline In-Context RL](https://mlsanity.com/paper/2502.17666/) (2025)

## Abstract (arXiv)

Offline reinforcement learning (RL) algorithms can acquire effective policies by utilizing previously collected experience, without any online interaction. It is widely understood that offline RL is able to extract good policies even from highly suboptimal data, a scenario where imitation learning finds suboptimal solutions that do not improve over the demonstrator that generated the dataset. However, another common use case for practitioners is to learn from data that resembles demonstrations. In this case, one can choose to apply offline RL, but can also use behavioral cloning (BC) algorithms, which mimic a subset of the dataset via supervised learning. Therefore, it seems natural to ask: when can an offline RL method outperform BC with an equal amount of expert data, even when BC is a natural choice? To answer this question, we characterize the properties of environments that allow offline RL methods to perform better than BC methods, even when only provided with expert data. Additionally, we show that policies trained on sufficiently noisy suboptimal data can attain better performance than even BC algorithms with expert data, especially on long-horizon problems. We validate our theoretical results via extensive experiments on both diagnostic and high-dimensional domains including robotic manipulation, maze navigation, and Atari games, with a variety of data distributions. We observe that, under specific but common conditions such as sparse rewards or noisy data sources, modern offline RL methods can significantly outperform BC.