Chih-Han Yang
@chih-han-yang · 1 works
Researching imitation learning methods from imperfect training data.
Recent posts by Chih-Han Yang
- Language-Critique Imitation Learning from Suboptimal Demonstrations - Prior work on imitation learning from suboptimal demonstrations typically relies on compressed supervision signals such as confidence estimates, discriminator scores, or importance weights. These… · Paper · arxiv.org