Article

HIDRA: A Hierarchical Dual-Routing Attention Framework for Replay-Free Lifelong Imitation Learning

The authors propose HIDRA, a hierarchical dual-attention routing framework for replay-free, single-pass lifelong imitation learning that decouples instruction-level expert retrieval from context-dependent refinement. The method introduces key-level geometric regularization that constrains within-task alignment and between-task separation to mitigate routing interference under representation drift. On several LIBERO benchmark suites, including variants with heterogeneous task sequences and paraphrased language instructions, HIDRA outperforms replay-free and replay baselines on AUC and forward transfer while maintaining low forgetting, and the code is publicly available.

Part of the event: HIDRA: A Routing Framework for Replay-Free Lifelong Imitation Learning

This page provides a summary and source link only.