SCIENCE@home

Meta-Reinforcement Learning With Evolving Gradient Regularization

Jiaxing Chen,Ao Ma,Shaofei Chen,Weilin Yuan,Zhenzhen Hu,Peng Li

Published 2025 in IEEE Robotics and Automation Letters

ABSTRACT

Deep reinforcement learning (DRL) typically requires reinitializing training for new tasks, limiting its generalization due to isolated knowledge transfer. Meta-reinforcement learning (Meta-RL) addresses this by enabling rapid adaptation through prior task experiences, yet existing gradient-based methods like MAML suffer from poor out-of-distribution performance due to overfitting narrow task distributions. To overcome this limitation, we propose Evolving Gradient Regularization MAML (ER-MAML). By integrating evolving gradient regularization into the MAML framework, ER-MAML optimizes meta-gradients while constraining adaptation directions via a regularization policy. This dual mechanism prevents overparameterization and enhances robustness across diverse task distributions. Experiments demonstrate ER-MAML outperforms state-of-the-art baselines by 14.6% in out-of-distribution success rates. It also achieves strong online adaptation performance in the MetaWorld benchmark. These results validate ER-MAML's effectiveness in improving meta-RL generalization under distribution shifts.

PUBLICATION RECORD

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-31 of 31 references · Page 1 of 1

CITED BY