← Search

Yuqi Bian

2 accepted papers

2025

Efficient Multi-agent Offline Coordination via Diffusion-based Trajectory Stitching

ICLR 2025poster

Learning from offline data without interacting with the environment is a promising way to fully leverage the intelligent decision-making capabilities of multi-agent reinforcement learning (MARL). Previous approaches have primarily focused on developing learning techniques, such as conservative metho…

Cited by 1SourcePDFScholar
2025

Learning to Reuse Policies in State Evolvable Environments

ICML 2025poster

The policy trained via reinforcement learning (RL) makes decisions based on sensor-derived state features. It is common for state features to evolve for reasons such as periodic sensor maintenance or the addition of new sensors for performance improvement. The deployed policy fails in new state spac…

Cited by 0SourcePDFScholar