4 papers
Reward as Observation: Learning Reward-Based Policies for Rapid Adaptation
Morgan Byrd, Maks Sorokin, Jacob Blevins +2
This paper explores a reward-based policy to achieve zero-shot transfer between source and target environments with completely different observation spaces. While humans can demons…
CF-JEPA: Improving Robustness of JEPA World Models via Controllability Factorization
Morgan Byrd, Robert Wright, Sehoon Ha
Controlling an agent with vision requires being able to separate useful information from irrelevant background information. JEPA-style latent world models seem like a natural appro…
AdaptManip: Learning Adaptive Whole-Body Object Lifting and Delivery with Online Recurrent State Estimation
Morgan Byrd, Donghoon Baek, Kartik Garg +5
This paper presents Adaptive Whole-body Loco-Manipulation, AdaptManip, a fully autonomous framework for humanoid robots to perform integrated navigation, object lifting, and delive…
PrivilegedDreamer: Explicit Imagination of Privileged Information for Rapid Adaptation of Learned Policies
Morgan Byrd, Jackson Crandell, Mili Das +3
Numerous real-world control problems involve dynamics and objectives affected by unobservable hidden parameters, ranging from autonomous driving to robotic manipulation, which caus…