{"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/cold-start-reinforcement-learning-with","title":"Cold-Start Reinforcement Learning with Softmax Policy Gradient","arxiv_id":"1709.09346","date":"2017-09-27","proceeding":"NeurIPS 2017 12","authors":["Nan Ding","Radu Soricut"],"abstract":"Policy-gradient approaches to reinforcement learning have two common and\nundesirable overhead procedures, namely warm-start training and sample variance\nreduction. In this paper, we describe a reinforcement learning method based on\na softmax value function that requires neither of these procedures. Our method\ncombines the advantages of policy-gradient methods with the efficiency and\nsimplicity of maximum-likelihood approaches. We apply this new cold-start\nreinforcement learning method in training sequence generation models for\nstructured output prediction problems. Empirical evidence validates this method\non automatic summarization and image captioning tasks.","url_abs":"http://arxiv.org/abs/1709.09346v2","url_pdf":"http://arxiv.org/pdf/1709.09346v2.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":"cold-start-reinforcement-learning-with","repo_url":"https://github.com/jacksonchen1998/Cold-Start-Reinforcement-Learning-with-Softmax-Policy-Gradient","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"policy-gradient-methods","task_name":"Policy Gradient Methods"},{"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":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1709.09346","atlas_url":"https://app.syntology.ai/?focus=1709.09346","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}