Multi-Step Likelihood-Ratio Correction for Reinforcement Learning with Verifiable Rewards

Documenti analoghi

• Latent Representation Alignment for Offline Goal-Conditioned Reinforcement Learning
  di: Kang, Hyungkyu, et al.
  Pubblicazione: (2026)
• Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning
  di: Kang, Hyungkyu, et al.
  Pubblicazione: (2025)
• Combinatorial Reinforcement Learning with Preference Feedback
  di: Lee, Joongkyu, et al.
  Pubblicazione: (2025)
• Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Options
  di: Lee, Joongkyu, et al.
  Pubblicazione: (2025)
• Peng's Q($λ$) for Conservative Value Estimation in Offline Reinforcement Learning
  di: Kim, Byeongchan, et al.
  Pubblicazione: (2026)