133 citations · 282 across the 33 of their papers we have counts for
7 papers · 1 filter
Fitted Occupancy-Ratio Evaluation without Bellman Completeness
Lars van der Laan, Nathan Kallus
Occupancy ratios correct distribution shift in offline reinforcement learning and are central to off-policy evaluation. Existing primal-dual and minimax methods typically estimate…
Soft Fitted Q-Iteration without Bellman Completeness: Occupancy Reweighting and Temperature Annealing
Lars van der Laan, Nathan Kallus
Fitted \(Q\)-iteration (FQI) is a standard regression-based method for optimal control in offline reinforcement learning, but its stability under function approximation often relie…
Fitted Q-Evaluation without Bellman Completeness via Occupancy Weighting
Lars van der Laan, Nathan Kallus
Fitted \(Q\)-evaluation (FQE) is a standard regression-based method for off-policy evaluation, but under distribution shift, value-function realizability alone does not ensure conv…
Bellman Calibration for -Learning in Offline Reinforcement Learning
Lars van der Laan, Nathan Kallus
Reliable long-horizon value prediction is difficult in offline reinforcement learning because fitted value methods combine bootstrapping, function approximation, and distribution s…
Semiparametric Double Reinforcement Learning with Applications to Long-Term Causal Inference
Lars van der Laan, David Hubbard, Allen Tran +2
Double reinforcement learning (DRL) provides efficient off-policy inference for policy values in nonparametric Markov decision processes (MDPs), but fully nonparametric estimators…
Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning
Aurélien Bibaut, Antoine Chambaz, Maria Dimakopoulou +2
Empirical risk minimization (ERM) is the workhorse of machine learning, whether for classification and regression or for off-policy policy learning, but its model-agnostic guarante…
Post-Contextual-Bandit Inference
Aurélien Bibaut, Antoine Chambaz, Maria Dimakopoulou +2
Contextual bandit algorithms are increasingly replacing non-adaptive A/B tests in e-commerce, healthcare, and policymaking because they can both improve outcomes for study particip…