Replacing the importance sampling ratio with a stop-gradient self-anchored ratio for positive advantages yields unclipped, REINFORCE-equivalent gradients that improve exploration without training instability.
Back to basics: Revisiting reinforce-style optimization for learning from human feedback in llms
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
citing papers explorer
-
UP: Unbounded Positive Asymmetric Optimization for Breaking the Exploration-Stability Dilemma
Replacing the importance sampling ratio with a stop-gradient self-anchored ratio for positive advantages yields unclipped, REINFORCE-equivalent gradients that improve exploration without training instability.
- CAPO: Critic-Guided Action-Aligned Policy Optimization for Advancing LLM Agent Capabilities