{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/from-credit-assignment-to-entropy","title":"From Credit Assignment to Entropy Regularization: Two New Algorithms for Neural Sequence Prediction","arxiv_id":"1804.10974","date":"2018-04-29","proceeding":"ACL 2018 7","authors":["Zihang Dai","Qizhe Xie","Eduard Hovy"],"abstract":"In this work, we study the credit assignment problem in reward augmented\nmaximum likelihood (RAML) learning, and establish a theoretical equivalence\nbetween the token-level counterpart of RAML and the entropy regularized\nreinforcement learning. Inspired by the connection, we propose two sequence\nprediction algorithms, one extending RAML with fine-grained credit assignment\nand the other improving Actor-Critic with a systematic entropy regularization.\nOn two benchmark datasets, we show the proposed algorithms outperform RAML and\nActor-Critic respectively, providing new alternatives to sequence prediction.","url_abs":"http://arxiv.org/abs/1804.10974v1","url_pdf":"http://arxiv.org/pdf/1804.10974v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"from-credit-assignment-to-entropy","repo_url":"https://github.com/zihangdai/ERAC-VAML","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.10974","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}