MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learning

Ähnliche Einträge

• Post-Training LLMs as Better Decision-Making Agents: A Regret-Minimization Approach
  von: Park, Chanwoo, et al.
  Veröffentlicht: (2025)
• Multi-Player Zero-Sum Markov Games with Networked Separable Interactions
  von: Park, Chanwoo, et al.
  Veröffentlicht: (2023)
• Do LLM Agents Have Regret? A Case Study in Online Learning and Games
  von: Park, Chanwoo, et al.
  Veröffentlicht: (2024)
• RLHF from Heterogeneous Feedback via Personalization and Preference Aggregation
  von: Park, Chanwoo, et al.
  Veröffentlicht: (2024)
• Offline Reinforcement Learning via Linear-Programming with Error-Bound Induced Constraints
  von: Ozdaglar, Asuman, et al.
  Veröffentlicht: (2022)