arXiv (All)
open access
Score Centering Stabilizes Off-policy Reinforcement Learning
Reinforcement learning (RL) of large language models is notoriously sensitive to small differences between training and inference engines, often referred to as the training-inference mismatch (TIM). However, completely eliminating TIM is impractical, as it would come at a major cost to rollout effic
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
- Score Centering Stabilizes Off-policy Reinforcement Learning#978408
- Large Language Models Hack Rewards, and Society#1129288
- PoEM: Predicting RL Outcomes from Existing Policies#1078297
- DE-Venus: A Data-Efficient RLVR Framework for Large Language Models#925667
- Unlocking the Unsolvable: Teacher-Guided Curriculum for Data-Efficient RLVR#1083480
Record · ID 1034599
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