A soft-surrogate estimator predicts a sequential policy's long-term value from short-horizon on-policy data and full-horizon historical data, with finite-sample guarantees.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Predicting Long Term Sequential Policy Value Using Softer Surrogates
A soft-surrogate estimator predicts a sequential policy's long-term value from short-horizon on-policy data and full-horizon historical data, with finite-sample guarantees.