{"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/alma-hierarchical-learning-for-composite","title":"ALMA: Hierarchical Learning for Composite Multi-Agent Tasks","arxiv_id":"2205.14205","date":"2022-05-27","proceeding":null,"authors":["Shariq Iqbal","Robby Costales","Fei Sha"],"abstract":"Despite significant progress on multi-agent reinforcement learning (MARL) in recent years, coordination in complex domains remains a challenge. Work in MARL often focuses on solving tasks where agents interact with all other agents and entities in the environment; however, we observe that real-world tasks are often composed of several isolated instances of local agent interactions (subtasks), and each agent can meaningfully focus on one subtask to the exclusion of all else in the environment. In these composite tasks, successful policies can often be decomposed into two levels of decision-making: agents are allocated to specific subtasks and each agent acts productively towards their assigned subtask alone. This decomposed decision making provides a strong structural inductive bias, significantly reduces agent observation spaces, and encourages subtask-specific policies to be reused and composed during training, as opposed to treating each new composition of subtasks as unique. We introduce ALMA, a general learning method for taking advantage of these structured tasks. ALMA simultaneously learns a high-level subtask allocation policy and low-level agent policies. We demonstrate that ALMA learns sophisticated coordination behavior in a number of challenging environments, outperforming strong baselines. ALMA's modularity also enables it to better generalize to new environment configurations. Finally, we find that while ALMA can integrate separately trained allocation and action policies, the best performance is obtained only by training all components jointly. Our code is available at https://github.com/shariqiqbal2810/ALMA","url_abs":"https://arxiv.org/abs/2205.14205v2","url_pdf":"https://arxiv.org/pdf/2205.14205v2.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":"alma-hierarchical-learning-for-composite","repo_url":"https://github.com/shariqiqbal2810/alma","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"multi-agent-reinforcement-learning","task_name":"Multi-agent Reinforcement Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.14205","atlas_url":"https://app.syntology.ai/?focus=2205.14205","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14205"}},"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":"deterministic:regex_extraction","url":"https://github.com/shariqiqbal2810/ALMA","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shariqiqbal2810/alma","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":"f945df5ee932ec6a","entry":"EntityAttentionLayer","repo":"shariqiqbal2810/alma","repo_kind":"official","path":"src/modules/agents/copa.py","file_url":"https://github.com/shariqiqbal2810/alma/blob/HEAD/src/modules/agents/copa.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f945df5ee932ec6a"}},{"code_sha256_prefix":"f5d07ed17c53c7fb","entry":"TaskEmbedder","repo":"shariqiqbal2810/alma","repo_kind":"official","path":"src/modules/agents/copa.py","file_url":"https://github.com/shariqiqbal2810/alma/blob/HEAD/src/modules/agents/copa.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f5d07ed17c53c7fb"}},{"code_sha256_prefix":"0fb8d41f329b4fbf","entry":"groupmask2attnmask","repo":"shariqiqbal2810/alma","repo_kind":"official","path":"src/modules/agents/copa.py","file_url":"https://github.com/shariqiqbal2810/alma/blob/HEAD/src/modules/agents/copa.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0fb8d41f329b4fbf"}},{"code_sha256_prefix":"8c29950e3e36e686","entry":"Coach","repo":"shariqiqbal2810/alma","repo_kind":"official","path":"src/modules/agents/copa.py","file_url":"https://github.com/shariqiqbal2810/alma/blob/HEAD/src/modules/agents/copa.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":"8c29950e3e36e686"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}