@article{inferencetimepolicyoptimizationforofflin, title = {Inference Time Policy Optimization for Offline RL with Differentiable World Models}, author = {Rohan Deb and Stephen J. Wright and Arindam Banerjee}, year = {2026}, eprint = {2603.22430}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.22430}, }