{"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/using-natural-language-and-program","title":"Using Natural Language and Program Abstractions to Instill Human Inductive Biases in Machines","arxiv_id":"2205.11558","date":"2022-05-23","proceeding":null,"authors":["Sreejan Kumar","Carlos G. Correa","Ishita Dasgupta","Raja Marjieh","Michael Y. Hu","Robert D. Hawkins","Nathaniel D. Daw","Jonathan D. Cohen","Karthik Narasimhan","Thomas L. Griffiths"],"abstract":"Strong inductive biases give humans the ability to quickly learn to perform a variety of tasks. Although meta-learning is a method to endow neural networks with useful inductive biases, agents trained by meta-learning may sometimes acquire very different strategies from humans. We show that co-training these agents on predicting representations from natural language task descriptions and programs induced to generate such tasks guides them toward more human-like inductive biases. Human-generated language descriptions and program induction models that add new learned primitives both contain abstract concepts that can compress description length. Co-training on these representations result in more human-like behavior in downstream meta-reinforcement learning agents than less abstract controls (synthetic language descriptions, program induction without learned primitives), suggesting that the abstraction supported by these representations is key.","url_abs":"https://arxiv.org/abs/2205.11558v3","url_pdf":"https://arxiv.org/pdf/2205.11558v3.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":"using-natural-language-and-program","repo_url":"https://github.com/sreejank/language_and_programs","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"meta-reinforcement-learning","task_name":"Meta Reinforcement Learning"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"program-induction","task_name":"Program induction"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.11558","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}