{"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/cooperative-inverse-reinforcement-learning","title":"Cooperative Inverse Reinforcement Learning","arxiv_id":"1606.03137","date":"2016-06-09","proceeding":"NeurIPS 2016 12","authors":["Dylan Hadfield-Menell","Anca Dragan","Pieter Abbeel","Stuart Russell"],"abstract":"For an autonomous system to be helpful to humans and to pose no unwarranted\nrisks, it needs to align its values with those of the humans in its environment\nin such a way that its actions contribute to the maximization of value for the\nhumans. We propose a formal definition of the value alignment problem as\ncooperative inverse reinforcement learning (CIRL). A CIRL problem is a\ncooperative, partial-information game with two agents, human and robot; both\nare rewarded according to the human's reward function, but the robot does not\ninitially know what this is. In contrast to classical IRL, where the human is\nassumed to act optimally in isolation, optimal CIRL solutions produce behaviors\nsuch as active teaching, active learning, and communicative actions that are\nmore effective in achieving value alignment. We show that computing optimal\njoint policies in CIRL games can be reduced to solving a POMDP, prove that\noptimality in isolation is suboptimal in CIRL, and derive an approximate CIRL\nalgorithm.","url_abs":"http://arxiv.org/abs/1606.03137v3","url_pdf":"http://arxiv.org/pdf/1606.03137v3.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":"cooperative-inverse-reinforcement-learning","repo_url":"https://github.com/chanlaw/assistive-bandits","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"cooperative-inverse-reinforcement-learning","repo_url":"https://github.com/rgreenblatt/ai_alignment_readings","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"},{"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=1606.03137","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}