{"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/actor-attention-critic-for-multi-agent","title":"Actor-Attention-Critic for Multi-Agent Reinforcement Learning","arxiv_id":"1810.02912","date":"2018-10-05","proceeding":"ICLR 2019 5","authors":["Shariq Iqbal","Fei Sha"],"abstract":"Reinforcement learning in multi-agent scenarios is important for real-world applications but presents challenges beyond those seen in single-agent settings. We present an actor-critic algorithm that trains decentralized policies in multi-agent settings, using centrally computed critics that share an attention mechanism which selects relevant information for each agent at every timestep. This attention mechanism enables more effective and scalable learning in complex multi-agent environments, when compared to recent approaches. Our approach is applicable not only to cooperative settings with shared rewards, but also individualized reward settings, including adversarial settings, as well as settings that do not provide global states, and it makes no assumptions about the action spaces of the agents. As such, it is flexible enough to be applied to most multi-agent learning problems.","url_abs":"https://arxiv.org/abs/1810.02912v2","url_pdf":"https://arxiv.org/pdf/1810.02912v2.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":"actor-attention-critic-for-multi-agent","repo_url":"https://github.com/shariqiqbal2810/MAAC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"actor-attention-critic-for-multi-agent","repo_url":"https://github.com/leehe228/LogisticsEnv","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"actor-attention-critic-for-multi-agent","repo_url":"https://github.com/parnika31/MACAAC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","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":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1810.02912","atlas_url":"https://app.syntology.ai/?focus=1810.02912","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.02912"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/parnika31/MACAAC","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shariqiqbal2810/MAAC","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/leehe228/LogisticsEnv","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":4,"ran":1,"repositories":1},"listed":{"samples":3,"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":"43c7e814609746ee","entry":"sample_gumbel","repo":"shariqiqbal2810/MAAC","repo_kind":"official","path":"utils/misc.py","file_url":"https://github.com/shariqiqbal2810/MAAC/blob/HEAD/utils/misc.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"43c7e814609746ee"}},{"code_sha256_prefix":"5d8ce3d017e5f6d8","entry":"get_display","repo":"parnika31/MACAAC","repo_kind":"listed","path":"multiagent/rendering.py","file_url":"https://github.com/parnika31/MACAAC/blob/HEAD/multiagent/rendering.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":"5d8ce3d017e5f6d8"}},{"code_sha256_prefix":"77260fe089db715e","entry":"gumbel_softmax_sample","repo":"shariqiqbal2810/MAAC","repo_kind":"official","path":"utils/misc.py","file_url":"https://github.com/shariqiqbal2810/MAAC/blob/HEAD/utils/misc.py","link_basis":"first_harvest_node","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":"77260fe089db715e"}},{"code_sha256_prefix":"f8dd361d2679d007","entry":"make_circle","repo":"parnika31/MACAAC","repo_kind":"listed","path":"multiagent/rendering.py","file_url":"https://github.com/parnika31/MACAAC/blob/HEAD/multiagent/rendering.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":"f8dd361d2679d007"}},{"code_sha256_prefix":"0fb08f714e49a890","entry":"make_env","repo":"shariqiqbal2810/MAAC","repo_kind":"official","path":"utils/make_env.py","file_url":"https://github.com/shariqiqbal2810/MAAC/blob/HEAD/utils/make_env.py","link_basis":"first_harvest_node","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":"0fb08f714e49a890"}},{"code_sha256_prefix":"ea4edded084fb348","entry":"make_polygon","repo":"parnika31/MACAAC","repo_kind":"listed","path":"multiagent/rendering.py","file_url":"https://github.com/parnika31/MACAAC/blob/HEAD/multiagent/rendering.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":"ea4edded084fb348"}},{"code_sha256_prefix":"e47eaea5616287c6","entry":"onehot_from_logits","repo":"shariqiqbal2810/MAAC","repo_kind":"official","path":"utils/misc.py","file_url":"https://github.com/shariqiqbal2810/MAAC/blob/HEAD/utils/misc.py","link_basis":"first_harvest_node","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":"e47eaea5616287c6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}