Marginalized importance weighting evaluates a target policy by reweighting offline state-action samples with its discounted occupancy ratio, characterized by an adjoint Bellman equation. Existing mini...
arXiv:2608.24858v1 Announce Type: new
Abstract: Marginalized importance weighting evaluates a target policy by reweighting offline state-action samples with its discounted occupancy ratio, characteri...
By 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 these ratios by enforcing occupancy-balance moments over a critic class.
arXiv:2607. 05375v1 Announce Type: cross Abstract: Occupancy ratios correct distribution shift in offline reinforcement learning and are central to off-policy evaluation.
By Lars van der Laan, Nathan Kallus
arXiv:2609.24489v1 Announce Type: new
Abstract: Offline reinforcement learning (RL) typically trains a critic by minimizing a regression loss against bootstrapped value targets stabilized by target n...
By Hyukjun Yang, Jongchan Park, Narim Jeong, Donghwan Lee
The paper introduces occupancy-weighted Fitted Q-Evaluation (FQE), a regression-based off‑policy evaluation method that replaces the standard offline distribution weights with a target‑policy discounted occupancy ratio. This weighting aligns the projection norm with the target policy’s dynamics, restoring contraction of the Bellman operator and eliminating the need for Bellman completeness. The authors provide finite‑sample guarantees that separate iteration, statistical, approximation, and ratio‑estimation errors, and show that exact occupancy weighting combined with fitted occupancy‑ratio evaluation yields consistent estimation under coverage without requiring critic‑side completeness.
By Lars van der Laan, Nathan Kallus