The reliable deployment of deep reinforcement learning in real-world settings requires the ability to generalize across a variety of conditions, including both in-distribution scenarios seen during training as well as novel out-of-distribution scenarios. In this work, we present a framework for dynamics generalization in deep reinforcement learning that unifies these two distinct types of generalization within a single architecture. We introduce a robust adaptation module that provides a mechanism for identifying and reacting to both in-distribution and out-of-distribution environment dynamics, along with a joint training pipeline that combines the goals of in-distribution adaptation and out-of-distribution robustness. Our algorithm GRAM achieves strong generalization performance across in-distribution and out-of-distribution scenarios upon deployment, which we demonstrate through extensive simulation and hardware locomotion experiments on a quadruped robot.
@article{arxiv.2412.04323,
title = {GRAM: Generalization in Deep RL with a Robust Adaptation Module},
author = {James Queeney and Xiaoyi Cai and Alexander Schperberg and Radu Corcodel and Mouhacine Benosman and Jonathan P. How},
journal= {arXiv preprint arXiv:2412.04323},
year = {2025}
}
Comments
Accepted for publication in IEEE Robotics and Automation Letters (RA-L)