Fine-Tuning on Self-Generated and Reward-Weighted Data: Learning Dynamics, Convergence Rates, and Benefits of Off-Policyness
cs.LG, math.OC
Submitted: 2026-09-29
Updated: 2026-09-29
Terminology
Sources
- OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework
- Kimi k1.5: Scaling Reinforcement Learning with LLMs
- Towards Principled, Practical Policy Gradient for Bandits and Tabular MDPs
- Delightful Gradients Accelerate Corner Escape
- OpenAI o1 System Card
- Trinity-RFT: A General-Purpose and Unified Framework for Reinforcement Fine-Tuning of Large Language Models
- Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)
- Success Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success
- Proximal Policy Optimization Algorithms
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks