arXiv (All)
open access
On KL-Regularized Policy Optimization
Asynchronous reinforcement learning (RL) for large language model (LLM) agents trains one policy on trajectories generated by another: rollouts come from stale checkpoints, and the inference engine's probabilities differ from the trainer's even at identical parameters. Standard remedies either clip
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Q-VGM: Q-Guided Value-Gradient Matching for Offline-to-Online RL of Flow-Matching VLA Policies#1014737
- CriPO: Enhancing Rubric-based RL via Self-Distillation#1117522
- DCRL: Decoupling and Coupling Reinforcement Learning via Policy-Reward Manifold Alignment#1064116
- Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models#820254
- Follow the Winners: Conservative Policy Improvement with the Cross-Entropy Method for Critic-Free RFT#1188039
Record · ID 1233002
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive