arXiv CS
open access
Enabling Token-wise Importance Sampling in Off-Policy RLVR with Proximal KL Regularization
Off-policy data in reinforcement learning with verifiable rewards (RLVR) can arise from asynchronous generation, rollout-training mismatch, and response reuse. Token-wise importance weighting avoids multiplying likelihood ratios across a response but generally biases policy gradients. We prove that,
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
- Enabling Token-wise Importance Sampling in Off-Policy RLVR with Proximal KL Regularization#1344235
- Group Adaptive Clipping Policy Optimization#819892
- Group Adaptive Clipping Policy Optimization#809896
- Gibbs-Gap Policy Optimization for Off-Policy RL with Verifiable Rewards#1355803
- ReFlow: Replay-Driven Decoupling for Efficient RL Post-Training#1357295
Record · ID 1319020
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