{"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/robust-multi-agent-coordination-via","title":"Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackers","arxiv_id":"2305.05909","date":"2023-05-10","proceeding":null,"authors":["Lei Yuan","Zi-Qian Zhang","Ke Xue","Hao Yin","Feng Chen","Cong Guan","Li-He Li","Chao Qian","Yang Yu"],"abstract":"Cooperative multi-agent reinforcement learning (CMARL) has shown to be promising for many real-world applications. Previous works mainly focus on improving coordination ability via solving MARL-specific challenges (e.g., non-stationarity, credit assignment, scalability), but ignore the policy perturbation issue when testing in a different environment. This issue hasn't been considered in problem formulation or efficient algorithm design. To address this issue, we firstly model the problem as a limited policy adversary Dec-POMDP (LPA-Dec-POMDP), where some coordinators from a team might accidentally and unpredictably encounter a limited number of malicious action attacks, but the regular coordinators still strive for the intended goal. Then, we propose Robust Multi-Agent Coordination via Evolutionary Generation of Auxiliary Adversarial Attackers (ROMANCE), which enables the trained policy to encounter diversified and strong auxiliary adversarial attacks during training, thus achieving high robustness under various policy perturbations. Concretely, to avoid the ego-system overfitting to a specific attacker, we maintain a set of attackers, which is optimized to guarantee the attackers high attacking quality and behavior diversity. The goal of quality is to minimize the ego-system coordination effect, and a novel diversity regularizer based on sparse action is applied to diversify the behaviors among attackers. The ego-system is then paired with a population of attackers selected from the maintained attacker set, and alternately trained against the constantly evolving attackers. Extensive experiments on multiple scenarios from SMAC indicate our ROMANCE provides comparable or better robustness and generalization ability than other baselines.","url_abs":"https://arxiv.org/abs/2305.05909v1","url_pdf":"https://arxiv.org/pdf/2305.05909v1.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":"robust-multi-agent-coordination-via","repo_url":"https://github.com/zzq-bot/romance","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"multi-agent-reinforcement-learning","task_name":"Multi-agent Reinforcement Learning"},{"task_slug":"smac","task_name":"SMAC"},{"task_slug":"smac-1","task_name":"SMAC+"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.05909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.05909"}},"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/zzq-bot/romance","reach":null}],"summary":{"ran":2,"unverified":3},"by_repo_kind":{"official":{"samples":5,"ran":2,"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":"e4933ddfeef19e88","entry":"DMAQ_SI_Weight","repo":"zzq-bot/romance","repo_kind":"official","path":"src/learners/dmaq_qatten_learner.py","file_url":"https://github.com/zzq-bot/romance/blob/HEAD/src/learners/dmaq_qatten_learner.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e4933ddfeef19e88"}},{"code_sha256_prefix":"6adbda391f36487c","entry":"Qatten_Weight","repo":"zzq-bot/romance","repo_kind":"official","path":"src/learners/dmaq_qatten_learner.py","file_url":"https://github.com/zzq-bot/romance/blob/HEAD/src/learners/dmaq_qatten_learner.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6adbda391f36487c"}},{"code_sha256_prefix":"3afc976a9a9dae68","entry":"DMAQ_QattenMixer","repo":"zzq-bot/romance","repo_kind":"official","path":"src/learners/dmaq_qatten_learner.py","file_url":"https://github.com/zzq-bot/romance/blob/HEAD/src/learners/dmaq_qatten_learner.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3afc976a9a9dae68"}},{"code_sha256_prefix":"21a1b9eab6308887","entry":"DMAQ_qattenLearner","repo":"zzq-bot/romance","repo_kind":"official","path":"src/learners/dmaq_qatten_learner.py","file_url":"https://github.com/zzq-bot/romance/blob/HEAD/src/learners/dmaq_qatten_learner.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"21a1b9eab6308887"}},{"code_sha256_prefix":"345fbcaf99999a3e","entry":"DMAQer","repo":"zzq-bot/romance","repo_kind":"official","path":"src/learners/dmaq_qatten_learner.py","file_url":"https://github.com/zzq-bot/romance/blob/HEAD/src/learners/dmaq_qatten_learner.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"345fbcaf99999a3e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}