# Improving Behavioural Cloning with Human-Driven Dynamic Dataset Augmentation

arXiv: https://arxiv.org/abs/2201.07719 · HTML: https://mlsanity.com/paper/2201.07719/

## Key facts

- Cited by 1 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 8 of its 15 references that are in the map.
- First posted on arXiv 19 Jan 2022.

## Placed in

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

## Builds on (most cited first, 8 of 8)

- [Behavioral Cloning from Observation](https://mlsanity.com/paper/1805.01954/) (2018)
- [Exploring the Limitations of Behavior Cloning for Autonomous Driving](https://mlsanity.com/paper/1904.08980/) (2019)
- [HG-DAgger: Interactive Imitation Learning with Human Experts](https://mlsanity.com/paper/1810.02890/) (2018)
- [MineRL: A Large-Scale Dataset of Minecraft Demonstrations](https://mlsanity.com/paper/1907.13440/) (2019)
- [End-to-End Robotic Reinforcement Learning without Reward Engineering](https://mlsanity.com/paper/1904.07854/) (2019)
- [The MineRL BASALT Competition on Learning from Human Feedback](https://mlsanity.com/paper/2107.01969/) (2021)
- [Benchmarking End-to-End Behavioural Cloning on Video Games](https://mlsanity.com/paper/2004.00981/) (2020)
- [Playing Minecraft with Behavioural Cloning](https://mlsanity.com/paper/2005.03374/) (2020)

## Built on by (most cited first, 1 of 1)

- [Search-Based Adversarial Estimates for Improving Sample Efficiency in Off-Policy Reinforcement Learning](https://mlsanity.com/paper/2502.01558/) (2025)

## Abstract (arXiv)

Behavioural cloning has been extensively used to train agents and is recognized as a fast and solid approach to teach general behaviours based on expert trajectories. Such method follows the supervised learning paradigm and it strongly depends on the distribution of the data. In our paper, we show how combining behavioural cloning with human-in-the-loop training solves some of its flaws and provides an agent task-specific corrections to overcome tricky situations while speeding up the training time and lowering the required resources. To do this, we introduce a novel approach that allows an expert to take control of the agent at any moment during a simulation and provide optimal solutions to its problematic situations. Our experiments show that this approach leads to better policies both in terms of quantitative evaluation and in human-likeliness.