Which Experiences Are Influential for RL Agents? Efficiently Estimating The Influence of Experiences

Documenti analoghi

• Consistency Trajectory Planning: High-Quality and Efficient Trajectory Optimization for Offline Model-Based Reinforcement Learning
  di: Wang, Guanquan, et al.
  Pubblicazione: (2025)
• CoverLib: Classifiers-equipped Experience Library by Iterative Problem Distribution Coverage Maximization for Domain-tuned Motion Planning
  di: Ishida, Hirokazu, et al.
  Pubblicazione: (2024)
• SLEA-RL: Step-Level Experience Augmented Reinforcement Learning for Multi-Turn Agentic Training
  di: Wang, Prince Zizhuang, et al.
  Pubblicazione: (2026)
• DrugSAGE:Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery
  di: Zhang, Yikun, et al.
  Pubblicazione: (2026)
• Efficient Preference-based Reinforcement Learning via Aligned Experience Estimation
  di: Bai, Fengshuo, et al.
  Pubblicazione: (2024)