Search

2 results for “imitation learning”

SIG//27857h agoCORL 2026 WORKSHOP

Evaluating Imitation Learning Policies for Robotic Manipulation Success

This research evaluates 281 imitation-learning policies for robotic manipulation, revealing critical design choices that affect performance. Key findings indicate that representation techniques significantly enhance success rates in real-world tasks.

SIG//852328d agoARXIV

Three-Stage Method for Multi-Task Learning in Legged Robots

This research presents a three-stage method for training legged robots to perform multiple tasks using reinforcement learning. The approach successfully combines skills like walking and digging, achieving high performance and robustness in real-world applications.