Language Models as Efficient Reward Function Searchers for Custom-Environment Multi-Objective Reinforcement

Documenti analoghi

• ERFSL: An Efficient Reward Function Searcher via Language Models for Custom-Environment Multi-Objective Optimization (Student Abstract)
  di: Xie, Guanwen, et al.
  Pubblicazione: (2026)
• Enhancing Information Freshness: An AoI Optimized Markov Decision Process
  di: Xu, Jingzehua, et al.
  Pubblicazione: (2024)
• Make Your AUV Adaptive: An Environment-Aware Reinforcement Learning Framework For Underwater Tasks
  di: Ding, Yimian, et al.
  Pubblicazione: (2025)
• AoI-MDP: An AoI Optimized Markov Decision Process (Student Abstract)
  di: Ding, Yimian, et al.
  Pubblicazione: (2026)
• Multi-Objective-Optimization Assisted Data Collection Framework for IoUT Based on Offline Reinforcement
  di: Ding, Yimian, et al.
  Pubblicazione: (2024)