PIPER enhances reinforcement learning using preference-based feedback to tackle sparse rewards.
― 6 min read
Utsav Singh
LGR2 improves robotic task performance through language instructions and hierarchical learning.
― 6 min read
DIPPER optimizes robot learning through human feedback, improving task performance.
― 6 min read
A new method helps robots perform tasks more effectively by breaking goals down.
― 5 min read