arXiv (All)
open access
Free Everywhere, Exact on Trees: PPO's Dropped Correction Buys Sample Efficiency Under Aggressive Reuse
Common policy improvement methods, including TRPO, PPO, and GRPO, estimate policy improvement under the behavioral policy's state-visitation distribution rather than the improved policy's own. The substitution makes the objective estimable from the behavioral policy's rollouts but adds a bias growin
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
- Clinical Use of a Contraceptive Decision Aid and Patient Outcomes#828539
- Selective Off-Policy Reference Tuning with Plan Guidance#1104439
- Modern Causal Inference Approaches to Improve Power for Subgroup Analysis in Randomized Controlled Trials.#236301
- Do Early Active Labor Market Policies Improve Outcomes of Not-Yet-Unemployed Workers? Findings from a Randomized Field Experiment#17373
- Mixed-effects Outcome-Adaptive Lasso for Propensity Score Estimation under Partial Interference#620765
Record · ID 1144601
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