{"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/is-independent-learning-all-you-need-in-the","title":"Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?","arxiv_id":"2011.09533","date":"2020-11-18","proceeding":null,"authors":["Christian Schroeder de Witt","Tarun Gupta","Denys Makoviichuk","Viktor Makoviychuk","Philip H. S. Torr","Mingfei Sun","Shimon Whiteson"],"abstract":"Most recently developed approaches to cooperative multi-agent reinforcement learning in the \\emph{centralized training with decentralized execution} setting involve estimating a centralized, joint value function. In this paper, we demonstrate that, despite its various theoretical shortcomings, Independent PPO (IPPO), a form of independent learning in which each agent simply estimates its local value function, can perform just as well as or better than state-of-the-art joint learning approaches on popular multi-agent benchmark suite SMAC with little hyperparameter tuning. We also compare IPPO to several variants; the results suggest that IPPO's strong performance may be due to its robustness to some forms of environment non-stationarity.","url_abs":"https://arxiv.org/abs/2011.09533v1","url_pdf":"https://arxiv.org/pdf/2011.09533v1.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":"is-independent-learning-all-you-need-in-the","repo_url":"https://github.com/16444take/aope-sim","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"is-independent-learning-all-you-need-in-the","repo_url":"https://github.com/anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"is-independent-learning-all-you-need-in-the","repo_url":"https://github.com/chauncygu/multi-agent-constrained-policy-optimisation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"is-independent-learning-all-you-need-in-the","repo_url":"https://github.com/cyanrain7/trpo-in-marl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"is-independent-learning-all-you-need-in-the","repo_url":"https://github.com/cyanrain7/trust-region-policy-optimisation-in-multi-agent-reinforcement-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"is-independent-learning-all-you-need-in-the","repo_url":"https://github.com/facebookresearch/benchmarl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"is-independent-learning-all-you-need-in-the","repo_url":"https://github.com/morning9393/HAPPO-HATRPO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"multi-agent-reinforcement-learning","task_name":"Multi-agent Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"smac","task_name":"SMAC"},{"task_slug":"smac-1","task_name":"SMAC+"},{"task_slug":"starcraft","task_name":"Starcraft"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"entropy-regularization","method_name":"Entropy Regularization"},{"method_slug":"ppo","method_name":"PPO"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2011.09533","atlas_url":"https://app.syntology.ai/?focus=2011.09533","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}