arXiv (OAI Expanded)
open access
When Greedy Sampling Explores: KL-Regularized Contextual Bandits without Eluder-Dimension Dependence
We study KL-regularized contextual bandits under both reward and preference feedback. While existing regret guarantees typically depend on the eluder dimension, we show that simple greedy sampling can achieve polylogarithmic regret without explicit dependence on this complexity measure. For reward f
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
- The Statistical Benefits of Multiple Responses for Learning from Demonstrations#1118003
- Elicitation and Decision Geometry in Single-Index Bandits#1130276
- Elicitation and Decision Geometry in Single-Index Bandits#1108766
- Statistical inference of additive monotone models and instance-optimality of multi-armed bandits and reinforcement learning#206992
- Sample Efficient Bayesian Optimization: From Local Search to Preference Learning#929144
Record · ID 1160767
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