4 papers · 1 filter
Cooperating with Future Collaborators: Multi-Agent RL under Staggered Participation
Jianglin Qiao, Siyi Hu, Thien Hoang Nguyen +2
In cooperative Multi-Agent Reinforcement Learning (MARL), agents are often trained under concurrent participation, while in many tasks some agents act earlier and leave task-releva…
Can We Trust the Teacher? Decoupled Credit Direction-Magnitude for Self-Distillation
Yugu Li, Zehong Cao, Peizhen Li +3
RLVR provides reliable trajectory-level credit, while OPSD offers dense supervision for token-level credit. This exposes a fundamental coupling when updating step-level credit dire…
RTPO: Reverse-Turn Policy Optimization for Stabilizing Agentic RL Training
Yugu Li, Zehong Cao, Jianglin Qiao +1
Training multi-turn agentic workflows with reinforcement learning (RL) enables large language models to perform complex reasoning, use external tools, and conduct iterative search…
Toward Adaptable Multi-Agent Reinforcement Learning: An Assumption-Aware Review
Siyi Hu, Mohamad A Hady, Jianglin Qiao +3
Multi-Agent Reinforcement Learning (MARL) has achieved strong performance in simulated benchmarks, yet real deployments often violate the assumptions under which algorithms are des…