@inproceedings{Corrado_Guided_2024,
	title={{Guided} {Data} {Augmentation} {for} {Offline} {Reinforcement} {Learning} {and} {Imitation} {Learning}},
	author={Corrado, Nicholas and Qu, Yuxiao and Balis, John U. and Labiosa, Adam and Hanna, Josiah P.},
	year={2024},
	month={August},
	booktitle={Proceedings of the Reinforcement Learning Conference (RLC)},
	abstract={
		In offline reinforcement learning (RL), RL agents learn to solve a task using only a fixed dataset of previously collected data. While offline RL has proven to be a viable method for learning real-world robot control policies, it typically requires large amounts of expert-quality data to learn effective policies that generalize to out-of-distribution states. Unfortunately, such data is often difficult and expensive to acquire in real-world tasks. Several recent works have leveraged data augmentation (DA) to inexpensively generate additional data, but most DA works apply augmentations in a random fashion and ultimately produce highly suboptimal augmented data. In this work, we propose \textbf{Gu}ided \textbf{D}ata \textbf{A}ugmentation (GuDA), a human-guided DA framework that generates expert-quality augmented data. The key insight behind GuDA is that while it may be difficult to demonstrate the sequence of actions required to produce expert data, a user can often easily characterize when an augmented trajectory segment represents progress toward task completion. Thus, a user can restrict the space of possible augmentations to automatically reject suboptimal augmented data. To extract a policy from GuDA, we use off-the-shelf offline reinforcement learning and behavior cloning algorithms. We evaluate GuDA on a physical robot soccer task as well as simulated D4RL navigation tasks, a simulated autonomous driving task, and a simulated soccer task. Empirically, GuDA enables learning given a small initial dataset of potentially suboptimal experience and outperforms a random DA strategy as well as a model-based DA strategy.
	},
}