arXiv (All)
open access
Not Every Divergence Should Be Suppressed: Counterfactual Recoverability in On-Policy Distillation
On-policy distillation (OPD) supervises student-visited trajectories, yet divergence-based rules cannot determine whether an erroneous prefix remains correctable. We formulate this decision as counterfactual recoverability and replay each error state through budget-matched teacher-continuation and r
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
- RL Starts before RL: On Policy Distillation for Better Reinforcement Learning#1064689
- Hierarchy as Constraint on Revision Validity: A Conceptual Account of Why Layered Adaptive Systems Learn When Flat Ones Merely React#167137
- Counterfactual Transition Graphs: Evaluating Cross-Class Transition Quality#482145
- OnlineCache: Learning Dynamic Caching Policies with Error Correction for Efficient Diffusion Inference#422263
- Diffusable Latents from Structure-Agnostic Distillation#1144624
Record · ID 1105129
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