@article{trajectoryorientedpolicyoptimizationwith, title = {Trajectory-Oriented Policy Optimization with Sparse Rewards}, author = {GuoJian Wang and Faguo Wu and Xiao Zhang}, year = {2024}, eprint = {2401.02225}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2401.02225v3}, }