Mildly Conservative Regularized Evaluation for Offline Reinforcement Learning.

Haohui Chen Zhiyong Chen Mildly Conservative Regularized Evaluation for Offline Reinforcement Learning. 2025 August abs/2508.05960 CoRR https://doi.org/10.48550/arXiv.2508.05960 db/journals/corr/corr2508.html#abs-2508-05960 streams/journals/corr