Quantile off-policy evaluation via deep conditional generative learning
Off-Policy evaluation (OPE) is concerned with evaluating a new target policy using offline
data generated by a potentially different behavior policy. It is critical in a number of …
data generated by a potentially different behavior policy. It is critical in a number of …
Off-policy evaluation in infinite-horizon reinforcement learning with latent confounders
Off-policy evaluation (OPE) in reinforcement learning is an important problem in settings
where experimentation is limited, such as healthcare. But, in these very same settings …
where experimentation is limited, such as healthcare. But, in these very same settings …
Off-policy evaluation for large action spaces via conjunct effect modeling
We study off-policy evaluation (OPE) of contextual bandit policies for large discrete action
spaces where conventional importance-weighting approaches suffer from excessive …
spaces where conventional importance-weighting approaches suffer from excessive …
Local metric learning for off-policy evaluation in contextual bandits with continuous actions
We consider local kernel metric learning for off-policy evaluation (OPE) of deterministic
policies in contextual bandits with continuous action spaces. Our work is motivated by …
policies in contextual bandits with continuous action spaces. Our work is motivated by …
Control variates for slate off-policy evaluation
N Vlassis, A Chandrashekar… - Advances in Neural …, 2021 - proceedings.neurips.cc
We study the problem of off-policy evaluation from batched contextual bandit data with
multidimensional actions, often termed slates. The problem is common to recommender …
multidimensional actions, often termed slates. The problem is common to recommender …
Balanced off-policy evaluation in general action spaces
Estimation of importance sampling weights for off-policy evaluation of contextual bandits
often results in imbalance—a mismatch between the desired and the actual distribution of …
often results in imbalance—a mismatch between the desired and the actual distribution of …
Policy-adaptive estimator selection for off-policy evaluation
Off-policy evaluation (OPE) aims to accurately evaluate the performance of counterfactual
policies using only offline logged data. Although many estimators have been developed …
policies using only offline logged data. Although many estimators have been developed …
State relevance for off-policy evaluation
Importance sampling-based estimators for off-policy evaluation (OPE) are valued for their
simplicity, unbiasedness, and reliance on relatively few assumptions. However, the variance …
simplicity, unbiasedness, and reliance on relatively few assumptions. However, the variance …
Towards Soft Fairness in Restless Multi-Armed Bandits
D Li, P Varakantham - arXiv preprint arXiv:2207.13343, 2022 - arxiv.org
Restless multi-armed bandits (RMAB) is a framework for allocating limited resources under
uncertainty. It is an extremely useful model for monitoring beneficiaries and executing timely …
uncertainty. It is an extremely useful model for monitoring beneficiaries and executing timely …
Doubly-Robust Off-Policy Evaluation with Estimated Logging Policy
We introduce a novel doubly-robust (DR) off-policy evaluation (OPE) estimator for Markov
decision processes, DRUnknown, designed for situations where both the logging policy and …
decision processes, DRUnknown, designed for situations where both the logging policy and …