English

Guided Data Augmentation for Offline Reinforcement Learning and Imitation Learning

Machine Learning 2024-08-09 v3 Robotics

Abstract

In offline reinforcement learning (RL), an RL agent learns to solve a task using only a fixed dataset of previously collected data. While offline RL has been successful in 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 experience. In this work, we propose Guided Data Augmentation (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.

Keywords

Cite

@article{arxiv.2310.18247,
  title  = {Guided Data Augmentation for Offline Reinforcement Learning and Imitation Learning},
  author = {Nicholas E. Corrado and Yuxiao Qu and John U. Balis and Adam Labiosa and Josiah P. Hanna},
  journal= {arXiv preprint arXiv:2310.18247},
  year   = {2024}
}

Comments

RLC 2024

R2 v1 2026-06-28T13:03:58.155Z