arXiv (All)
open access
Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening
In reinforcement learning for large language models, Proximal Policy Optimization (PPO) commonly uses a critic to estimate state values and reduce the variance of policy updates. However, we uncover a systematic failure mode in PPO critics, which we call Value Flattening: state values, estimated fro
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
- Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening#965423
- DMRL: Document-Mediated Reinforcement Learning for Skill Optimization in Advertising Recommendation#822565
- Transductive Off-policy Proximal Policy Optimization#1049578
- Offline Policy Evaluation via Mixed Bellman Residuals and Adaptive Critic Representations#1117898
- Gradient-Gated DPO: Stabilizing Preference Optimization in Language Models#1049823
Record · ID 1012877
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