← Back to Benchmarks
simmediumimitationmetric · varies

M2Distill: Multi-Modal Distillation for Lifelong Imitation Learning

Description

Lifelong imitation learning for manipulation tasks poses significant challenges due to distribution shifts that occur in incremental learning steps. Existing methods often focus on unsupervised skill discovery to construct an ever-growing skill library or distillation from multiple policies, which can lead to scalability issues as diverse manipulation tasks are continually introduced and may fail to ensure a consistent latent space throughout the learning process, leading to catastrophic forgett

Source

http://arxiv.org/abs/2410.00064v3