Demonstration and offset augmented meta reinforcement learning with sparse rewards

Demonstration and offset augmented meta reinforcement learning with sparse rewards

Abstract This paper introduces DOAMRL, a novel meta-reinforcement learning (meta-RL) method that extends the Model-Agnostic Meta-Learning (MAML) framework. The method addresses a key limitation of existing meta-RL approaches, which struggle to effectively use suboptimal demonstrations to guide train...

Full description

Bibliographic Details
Main Authors: Haorui Li, Jiaqi Liang, Xiaoxuan Wang, Chengzhi Jiang, Linjing Li, Daniel Zeng
Format: Article
Language:English
Published: Springer 2025-02-01
Series:Complex & Intelligent Systems
Subjects:
Meta learning
Reinforcement learning
Sparse reward
Suboptimal demonstration
One-shot learning
Imitation learning
Online Access:https://doi.org/10.1007/s40747-025-01785-0

Internet

https://doi.org/10.1007/s40747-025-01785-0

Similar Items