CAIMAN: Causal Action Influence Detection for Sample-efficient Loco-manipulation

Understand

Enabling legged robots to perform non-prehensile loco-manipulation is crucial for enhancing their versatility.

• Learning behaviors such as whole-body object pushing often requires sophisticated planning strategies or extensive task-specific reward shaping, especially in unstructured environments.
• In this work, we present CAIMAN, a practical reinforcement learning framework that encourages the agent to gain control over other entities in the environment.
• CAIMAN leverages causal action influence as an intrinsic motivation objective, allowing legged robots to efficiently acquire object pushing skills even under sparse task rewards.