@article{matchorreplayselfimitatingproximalpolicy, title = {Match or Replay: Self Imitating Proximal Policy Optimization}, author = {Gaurav Chaudhary and Laxmidhar Behera and Washim Uddin Mondal}, year = {2026}, eprint = {2603.27515}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.27515}, }