# Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning

arXiv: https://arxiv.org/abs/2407.15007 · HTML: https://mlsanity.com/paper/2407.15007/

## Key facts

- Cited by 74 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.
- First posted on arXiv 20 Jul 2024.

## Placed in

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

## Built on by (most cited first, 30 of 74)

- [What Can RL Bring to VLA Generalization? An Empirical Study](https://mlsanity.com/paper/2505.19789/) (2025)
- [Scaling Test-Time Compute Without Verification or RL is Suboptimal](https://mlsanity.com/paper/2502.12118/) (2025)
- [Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challenges](https://mlsanity.com/paper/2505.04769/) (2025)
- [VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators](https://mlsanity.com/paper/2510.00406/) (2025)
- [Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction](https://mlsanity.com/paper/2506.07976/) (2025)
- [ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning](https://mlsanity.com/paper/2410.09486/) (2024)
- [A Theory of Learning with Autoregressive Chain of Thought](https://mlsanity.com/paper/2503.07932/) (2025)
- [Diffusing States and Matching Scores: A New Framework for Imitation Learning](https://mlsanity.com/paper/2410.13855/) (2024)
- [Affordance Field Intervention: Enabling VLAs to Escape Memory Traps in Robotic Manipulation](https://mlsanity.com/paper/2512.07472/) (2025)
- [Optimistically Optimistic Exploration for Provably Efficient Infinite-Horizon Reinforcement and Imitation Learning](https://mlsanity.com/paper/2502.13900/) (2025)
- [SPINE: Token-Selective Test-Time Reinforcement Learning with Entropy-Band Regularization](https://mlsanity.com/paper/2511.17938/) (2025)
- [Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds](https://mlsanity.com/paper/2408.08994/) (2024)
- [Reinforcement Learning from Rich Feedback with Distributional DAgger](https://mlsanity.com/paper/2606.05152/) (2026)
- [Active Fine-Tuning of Multi-Task Policies](https://mlsanity.com/paper/2410.05026/) (2024)
- [The Central Role of the Loss Function in Reinforcement Learning](https://mlsanity.com/paper/2409.12799/) (2024)
- [Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels](https://mlsanity.com/paper/2510.06499/) (2025)
- [Autoregressive Language Models are Secretly Energy-Based Models: Insights into the Lookahead Capabilities of Next-Token Prediction](https://mlsanity.com/paper/2512.15605/) (2025)
- [Computational Algebra with Attention: Transformer Oracles for Border Basis Algorithms](https://mlsanity.com/paper/2505.23696/) (2025)
- [Learning to Answer from Correct Demonstrations](https://mlsanity.com/paper/2510.15464/) (2025)
- [Provably and Practically Efficient Adversarial Imitation Learning with General Function Approximation](https://mlsanity.com/paper/2411.00610/) (2024)
- [IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic](https://mlsanity.com/paper/2502.19859/) (2025)
- [Inverse Q-Learning Done Right: Offline Imitation Learning in Qπ-Realizable MDPs](https://mlsanity.com/paper/2505.19946/) (2025)
- [Behavioral Exploration: Learning to Explore via In-Context Adaptation](https://mlsanity.com/paper/2507.09041/) (2025)
- [Inverse Reinforcement Learning with Just Classification and a Few Regressions](https://mlsanity.com/paper/2509.21172/) (2025)
- [Improved Bounds for Private and Robust Alignment](https://mlsanity.com/paper/2512.23816/) (2025)
- [Learning Equilibria from Data: Provably Efficient Multi-Agent Imitation Learning](https://mlsanity.com/paper/2505.17610/) (2025)
- [Meet Dynamic Individual Preferences: Resolving Conflicting Human Value with Paired Fine-Tuning](https://mlsanity.com/paper/2604.12479/) (2026)
- [Learning Visual Feature-Based World Models via Residual Latent Action](https://mlsanity.com/paper/2605.07079/) (2026)
- [EMA Without the Lag: Bias-Corrected Iterate Averaging Schemes](https://mlsanity.com/paper/2508.00180/) (2025)
- [To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable Reinforcement Learning](https://mlsanity.com/paper/2510.03207/) (2025)

## Abstract (arXiv)

Imitation learning (IL) aims to mimic the behavior of an expert in a sequential decision making task by learning from demonstrations, and has been widely applied to robotics, autonomous driving, and autoregressive text generation. The simplest approach to IL, behavior cloning (BC), is thought to incur sample complexity with unfavorable quadratic dependence on the problem horizon, motivating a variety of different online algorithms that attain improved linear horizon dependence under stronger assumptions on the data and the learner's access to the expert. We revisit the apparent gap between offline and online IL from a learning-theoretic perspective, with a focus on the realizable/well-specified setting with general policy classes up to and including deep neural networks. Through a new analysis of behavior cloning with the logarithmic loss, we show that it is possible to achieve horizon-independent sample complexity in offline IL whenever (i) the range of the cumulative payoffs is controlled, and (ii) an appropriate notion of supervised learning complexity for the policy class is controlled. Specializing our results to deterministic, stationary policies, we show that the gap between offline and online IL is smaller than previously thought: (i) it is possible to achieve linear dependence on horizon in offline IL under dense rewards (matching what was previously only known to be achievable in online IL); and (ii) without further assumptions on the policy class, online IL cannot improve over offline IL with the logarithmic loss, even in benign MDPs. We complement our theoretical results with experiments on standard RL tasks and autoregressive language generation to validate the practical relevance of our findings.