PROMO: Preference-conditioned Multi-Objective Reinforcement Learning for Quadrupedal Robots

Name: PROMO: Preference-conditioned Multi-Objective Reinforcement Learning for Quadrupedal Robots
Uploaded: 2026-10-05T10:59:25.343737+00:00
Duration: 338 s
Description: PROMO introduces Preference-Conditioned Multi-Objective Reinforcement Learning (MORL) for quadrupedal robots. It allows a single policy to adapt its behavior dynamically based on operator preferences—like prioritizing tracking, stability, or efficiency—at runtime. This enables robots to trade off locomotion objectives without needing separate controllers or retraining.

PROMO introduces Preference-Conditioned Multi-Objective Reinforcement Learning (MORL) for quadrupedal robots. It allows a single policy to adapt its behavior dynamically based on operator preferences—like prioritizing tracking, stability, or efficiency—at runtime. This enables robots to trade off locomotion objectives without needing separate controllers or retraining.

Open the full episode