Track manipulation, locomotion and embodied systems.
Search papers, labs, and topics across Lattice.
We introduce MASkillBlender, a decentralized multi-agent reinforcement learning framework for coordinated multi-humanoid loco-manipulation that addresses challenges in high-dimensional control and scalability. The framework learns a shared decentralized high-level policy over reusable pre-trained single-humanoid skills, enabling coordinated behaviors with only task-level rewards and eliminating the need for task-specific motion references. A permutation-based data augmentation strategy is employed to enhance learning efficiency for homogeneous systems, with theoretical guarantees on preserving policy-gradient direction.
Coordinated multi-humanoid loco-manipulation is achieved by a single decentralized policy that dynamically blends pre-trained single-humanoid skills, bypassing task-specific motion generation.
Coordinated multi-humanoid loco-manipulation is promising yet challenging due to high-dimensional whole-body control, decentralized decision making, and scalability. While recent reinforcement learning methods have improved single-humanoid whole-body control, extending them to the multi-humanoid setting remains nontrivial and often requires substantial reward engineering or task-specific design. We propose MASkillBlender, a general multi-agent reinforcement learning framework to achieve decentralized multi-humanoid whole-body coordination. By learning a shared decentralized high-level policy over reusable pre-trained single-humanoid skills, MASkillBlender enables coordinated behaviors using only task-level rewards, without requiring task-specific motion references. To improve learning efficiency, we further introduce a permutation-based data augmentation strategy for homogeneous multi-humanoid systems, and theoretically show that the permuted samples preserve the policy-gradient direction of the original samples under the homogeneous Markov game formulation. We evaluate MASkillBlender on multiple multi-humanoid coordination tasks across two humanoid embodiments. Simulation results demonstrate that the proposed framework consistently achieves strong task performance and enables coordinated behaviors across different tasks and humanoid embodiments.