{"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/discovering-diverse-multi-agent-strategic-1","title":"Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization","arxiv_id":"2103.04564","date":"2021-03-08","proceeding":"ICLR 2021 1","authors":["Zhenggang Tang","Chao Yu","Boyuan Chen","Huazhe Xu","Xiaolong Wang","Fei Fang","Simon Du","Yu Wang","Yi Wu"],"abstract":"We propose a simple, general and effective technique, Reward Randomization for discovering diverse strategic policies in complex multi-agent games. Combining reward randomization and policy gradient, we derive a new algorithm, Reward-Randomized Policy Gradient (RPG). RPG is able to discover multiple distinctive human-interpretable strategies in challenging temporal trust dilemmas, including grid-world games and a real-world game Agar.io, where multiple equilibria exist but standard multi-agent policy gradient algorithms always converge to a fixed one with a sub-optimal payoff for every player even using state-of-the-art exploration techniques. Furthermore, with the set of diverse strategies from RPG, we can (1) achieve higher payoffs by fine-tuning the best policy from the set; and (2) obtain an adaptive agent by using this set of strategies as its training opponents. The source code and example videos can be found in our website: https://sites.google.com/view/staghuntrpg.","url_abs":"https://arxiv.org/abs/2103.04564v2","url_pdf":"https://arxiv.org/pdf/2103.04564v2.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":"discovering-diverse-multi-agent-strategic-1","repo_url":"https://github.com/staghuntrpg/RPG","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"discovering-diverse-multi-agent-strategic-1","repo_url":"https://github.com/staghuntrpg/agar","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2103.04564","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}