3 articles tagged with #trust-region. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers introduce Trust Region Q-Adjoint Matching (TRQAM), a reinforcement learning algorithm that stabilizes off-policy fine-tuning of pretrained flow policies by adaptively controlling deviation through trust-region constraints. The method demonstrates significant performance improvements, achieving 68% success rate on offline RL tasks compared to 46% for previous approaches.
Researchers propose Proximal Supervised Fine-Tuning (PSFT), a new method that applies trust-region constraints from reinforcement learning to improve how foundation models adapt to new tasks. The technique maintains model capabilities while fine-tuning, outperforming standard supervised fine-tuning on out-of-domain generalization tasks.
Researchers propose Trust Region Masking (TRM) to address off-policy mismatch problems in Large Language Model reinforcement learning pipelines. The method provides the first non-vacuous monotonic improvement guarantees for long-horizon LLM-RL tasks by masking entire sequences that violate trust region constraints.
