MARLIN: Language negotiation-guided multi-agent reinforcement learning
What happened
Toby Godfrey, William Hunt, and Mohammad D. Soorati released MARLIN, a hybrid framework: before reinforcement learning policies have learned effective behavior, a large language model generates high-level action plans through language negotiation between robots to guide policy learning, dynamically switching between reinforcement learning and language model negotiation during training. The authors evaluated it in simulation and on physical robots using local and remote language models, respectively, and report that compared with standard multi-agent reinforcement learning, the method achieves higher early-training performance with limited impact on final performance. The code is publicly available, and the paper was accepted to ROBIO2026.
AI 根据报道生成 · 6 days ago更新
Reporting timeline
Follow the reporting to explore different perspectives.
- arXiv cs.ROMARLIN: Guiding Multi-Agent Reinforcement Learning with Language Negotiation
MARLIN proposes a hybrid framework in which large language models guide policy learning by generating high-level action plans through inter-robot language negotiation before the reinforcement learning policy has learned effective behaviors, and it dynamically switches between reinforcement learning and language-model negotiation during training. The authors evaluated it on simulated and physical robots with local and remote language models; results show higher early-training performance than standard multi-agent reinforcement learning, with limited impact on final performance. The code is publicly available, and the paper was accepted to ROBIO2026.
Activity for this event
- Current
- 3
- Peak
- 10Nov 5 14:00
- Past 24 hours
- -49%
The trend compares participants observed throughout the same period, so its range may be smaller than the current interest count. Move or tap to inspect each hour; use the arrow keys on a keyboard.