{"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/marllib-extending-rllib-for-multi-agent","title":"MARLlib: A Scalable and Efficient Multi-agent Reinforcement Learning Library","arxiv_id":"2210.13708","date":"2022-10-11","proceeding":null,"authors":["Siyi Hu","Yifan Zhong","Minquan Gao","Weixun Wang","Hao Dong","Xiaodan Liang","Zhihui Li","Xiaojun Chang","Yaodong Yang"],"abstract":"A significant challenge facing researchers in the area of multi-agent reinforcement learning (MARL) pertains to the identification of a library that can offer fast and compatible development for multi-agent tasks and algorithm combinations, while obviating the need to consider compatibility issues. In this paper, we present MARLlib, a library designed to address the aforementioned challenge by leveraging three key mechanisms: 1) a standardized multi-agent environment wrapper, 2) an agent-level algorithm implementation, and 3) a flexible policy mapping strategy. By utilizing these mechanisms, MARLlib can effectively disentangle the intertwined nature of the multi-agent task and the learning process of the algorithm, with the ability to automatically alter the training strategy based on the current task's attributes. The MARLlib library's source code is publicly accessible on GitHub: \\url{https://github.com/Replicable-MARL/MARLlib}.","url_abs":"https://arxiv.org/abs/2210.13708v4","url_pdf":"https://arxiv.org/pdf/2210.13708v4.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":"marllib-extending-rllib-for-multi-agent","repo_url":"https://github.com/replicable-marl/marllib","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"multi-agent-reinforcement-learning","task_name":"Multi-agent Reinforcement 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":[{"method_slug":null,"method_name":"Library"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.13708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.13708"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/replicable-marl/marllib","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"a1eed76af82706d7","entry":"check_algo_type","repo":"replicable-marl/marllib","repo_kind":"official","path":"marllib/marl/common.py","file_url":"https://github.com/replicable-marl/marllib/blob/HEAD/marllib/marl/common.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a1eed76af82706d7"}},{"code_sha256_prefix":"3c30367ff730506e","entry":"dict_update","repo":"replicable-marl/marllib","repo_kind":"official","path":"marllib/marl/common.py","file_url":"https://github.com/replicable-marl/marllib/blob/HEAD/marllib/marl/common.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c30367ff730506e"}},{"code_sha256_prefix":"06edcda225a9f4e4","entry":"normalize_action","repo":"replicable-marl/marllib","repo_kind":"official","path":"marllib/envs/base_env/mamujoco.py","file_url":"https://github.com/replicable-marl/marllib/blob/HEAD/marllib/envs/base_env/mamujoco.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"06edcda225a9f4e4"}},{"code_sha256_prefix":"7127a59833466d3d","entry":"normalize_obs","repo":"replicable-marl/marllib","repo_kind":"official","path":"marllib/envs/base_env/mamujoco.py","file_url":"https://github.com/replicable-marl/marllib/blob/HEAD/marllib/envs/base_env/mamujoco.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7127a59833466d3d"}},{"code_sha256_prefix":"d01cc2fe369f8312","entry":"recursive_dict_update","repo":"replicable-marl/marllib","repo_kind":"official","path":"marllib/marl/common.py","file_url":"https://github.com/replicable-marl/marllib/blob/HEAD/marllib/marl/common.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d01cc2fe369f8312"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}