Jul 2026
Learning from success: efficient selective learning methods for multi-agent sparse-reward tasks
This paper proposes effective multi-agent selective learning methods to boost sample-efficient training by learning from successful experiences, and adopts a retrogression-based selection method to identify successful agent trajectories from the team rewards.
Xinning Chen, Xuan Liu, Yanwen Ba et al.
· CCF Transactions on Pervasiv... · 0 citations