Research map / Reinforcement learning / RL from feedback

Group-Relative REINFORCE Is Secretly an Off-Policy Algorithm: Demystifying Some Myths About GRPO and Its Friends

ICLR 2026 · Reinforcement learning › RL from feedback · approach: GRPO stability and variants

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Closest papers by meaning

• Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards (NeurIPS 2025 · similarity 0.92)
• TIC-GRPO: Provable and Efficient Optimization for Reinforcement Learning from Human Feedback (NeurIPS 2026 · similarity 0.91)
• GVPO: Group Variance Policy Optimization for Large Language Model Post-Training (NeurIPS 2025 · similarity 0.90)
• Stronger-MAS: Multi-Agent Reinforcement Learning for Collaborative LLMs (ICLR 2026 · similarity 0.90)
• On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization (NeurIPS 2025 · similarity 0.89)
• $f$-GRPO & Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment (NeurIPS 2026 · similarity 0.89)