{"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/maven-multi-agent-variational-exploration","title":"MAVEN: Multi-Agent Variational Exploration","arxiv_id":"1910.07483","date":"2019-10-16","proceeding":"NeurIPS 2019 12","authors":["Anuj Mahajan","Tabish Rashid","Mikayel Samvelyan","Shimon Whiteson"],"abstract":"Centralised training with decentralised execution is an important setting for cooperative deep multi-agent reinforcement learning due to communication constraints during execution and computational tractability in training. In this paper, we analyse value-based methods that are known to have superior performance in complex environments [43]. We specifically focus on QMIX [40], the current state-of-the-art in this domain. We show that the representational constraints on the joint action-values introduced by QMIX and similar methods lead to provably poor exploration and suboptimality. Furthermore, we propose a novel approach called MAVEN that hybridises value and policy-based methods by introducing a latent space for hierarchical control. The value-based agents condition their behaviour on the shared latent variable controlled by a hierarchical policy. This allows MAVEN to achieve committed, temporally extended exploration, which is key to solving complex multi-agent tasks. Our experimental results show that MAVEN achieves significant performance improvements on the challenging SMAC domain [43].","url_abs":"https://arxiv.org/abs/1910.07483v2","url_pdf":"https://arxiv.org/pdf/1910.07483v2.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":"maven-multi-agent-variational-exploration","repo_url":"https://github.com/AnujMahajanOxf/MAVEN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"maven-multi-agent-variational-exploration","repo_url":"https://github.com/Denys88/rl_games","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"maven-multi-agent-variational-exploration","repo_url":"https://github.com/chandar-lab/coe","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"maven-multi-agent-variational-exploration","repo_url":"https://github.com/starry-sky6688/marl-algorithms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"multi-agent-reinforcement-learning","task_name":"Multi-agent Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"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=1910.07483","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.07483"}},"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/AnujMahajanOxf/MAVEN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/starry-sky6688/marl-algorithms","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Denys88/rl_games","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chandar-lab/coe","reach":null}],"summary":{"ran_draft_wrong":1,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1},"listed":{"samples":1,"ran":1,"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":2,"samples":[{"code_sha256_prefix":"d95214ebaa722aa0","entry":"build_td_lambda_targets","repo":"AnujMahajanOxf/MAVEN","repo_kind":"official","path":"maven_code/src/utils/rl_utils.py","file_url":"https://github.com/AnujMahajanOxf/MAVEN/blob/HEAD/maven_code/src/utils/rl_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d95214ebaa722aa0"}},{"code_sha256_prefix":"930812c3b06fc858","entry":"work","repo":"chandar-lab/coe","repo_kind":"listed","path":"src/search.py","file_url":"https://github.com/chandar-lab/coe/blob/HEAD/src/search.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"930812c3b06fc858"}},{"code_sha256_prefix":"42d9ef9f315eb821","entry":"build_td_lambda_targets__old","repo":"AnujMahajanOxf/MAVEN","repo_kind":"official","path":"maven_code/src/utils/rl_utils.py","file_url":"https://github.com/AnujMahajanOxf/MAVEN/blob/HEAD/maven_code/src/utils/rl_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"42d9ef9f315eb821"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}