← Back to Benchmarks
simmediumquadrupedmetric · varies

Self-adapting Robotic Agents through Online Continual Reinforcement Learning with World Model Feedback

Description

As learning-based robotic controllers are typically trained offline and deployed with fixed parameters, their ability to cope with unforeseen changes during operation is limited. Biologically inspired, this work presents a framework for online Continual Reinforcement Learning that enables automated adaptation during deployment. Building on DreamerV3, a model-based Reinforcement Learning algorithm, the proposed method leverages world model prediction residuals to detect out-of-distribution events

Source

http://arxiv.org/abs/2603.04029v1