Breaking the Curse of Horizon¶
Liu, Q., Li, Tang, & Zhou, D. (2018). Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation. Advances in Neural Information Processing Systems.
Cited by¶
1 citation across 1 artifact.
Each citation links to the sentence it supports in the citing article.
Mechanisms¶
- Off-Policy Evaluation
- Where the candidate would do things the logging policy almost never did, the logs hold little relevant evidence, importance weights explode, and the estimate's variance balloons — the "curse of horizon" that makes long-sequence off-policy estimates notoriously unstable.
This sourceShows that trajectory-wise importance ratios compound multiplicatively, causing importance-sampling variance to grow rapidly with horizon.
- Where the candidate would do things the logging policy almost never did, the logs hold little relevant evidence, importance weights explode, and the estimate's variance balloons — the "curse of horizon" that makes long-sequence off-policy estimates notoriously unstable.
Verification¶
Does it exist? Not checked yet. This entry carries no identifier to resolve. It was extracted from the citation as written in the article, normalized, and deduplicated against the rest of the registry.
Does it back the claim? Not recorded. The single citation of this work carries no recorded support check.
Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.
See how references were verified.
Registry ID ref:8545d589bfb9 · see in the full table