75 - Reinforcement / Imitation Learning in NLP, with Hal Daume III
In this episode, we invite Hal Daum\xe9 to continue the discussion on reinforcement learning, focusing on how it has been used in NLP. We discuss how to reduce NLP problems into the reinforcement learning framework, and circumstances where it may or may not be useful. We discuss imitation learning, roll-in and roll-out, and how to approximate an expert with a reference policy. \n\nDAgger: https://www.semanticscholar.org/paper/A-Reduction-of-Imitation-Learning-and-Structured-to-Ross-Gordon/17eddf33b513ae1134abadab728bdbf6abab2a05?navId=citing-papers\nRESLOPE: http://legacydirs.umiacs.umd.edu/~hal/docs/daume18reslope.pdf