<script async class=”docswell-embed” src=”https://www.docswell.com/assets/libs/docswell-embed/docswell-embed.min.js” data-src=”https://www.docswell.com/slide/KGXWYJ/embed” data-aspect=”0.5625″></script><div class=”docswell-link”><a href=”https://www.docswell.com/s/DeepLearning2023/KGXWYJ-2023-09-28-140631″>【DL輪読会】Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback by @DeepLearning2023</a></div>