Pairwise Bellman validation selects off-policy estimators without extra critics
Unweighted PBV is competitive on Hopper and Deep OPE; target-occupancy weighting can help under controlled overlap.
Stories per day · 30 days
3 stories, newest first · one card per story
Stories tagged #off-policy-evaluation
Optimal Sequential Annotations for Off-Policy Evaluation
Paper optimizes sequential annotation budgets for doubly robust off-policy evaluation of complex outcomes.
Exponential Hardness of Off-Policy Evaluation under History-Dependent Logging
Researchers prove off-policy evaluation under history-dependent logging requires exponentially many episodes, resolving a hardness question for model-based POMDP evaluation.