@misc{butt2024codeit, title={CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay}, author={Natasha Butt and Blazej Manczak and Auke Wiggers and Corrado Rainone and David Zhang and Michaƫl Defferrard and Taco Cohen}, year={2024}, eprint={2402.04858}, archivePrefix={arXiv}, primaryClass={cs.AI}, url={https://arxiv.org/abs/2402.04858} }