{"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/ai-qmix-attention-and-imagination-for-dynamic","title":"Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning","arxiv_id":"2006.04222","date":"2020-06-07","proceeding":null,"authors":["Shariq Iqbal","Christian A. Schroeder de Witt","Bei Peng","Wendelin Böhmer","Shimon Whiteson","Fei Sha"],"abstract":"Multi-agent settings in the real world often involve tasks with varying types and quantities of agents and non-agent entities; however, common patterns of behavior often emerge among these agents/entities. Our method aims to leverage these commonalities by asking the question: ``What is the expected utility of each agent when only considering a randomly selected sub-group of its observed entities?'' By posing this counterfactual question, we can recognize state-action trajectories within sub-groups of entities that we may have encountered in another task and use what we learned in that task to inform our prediction in the current one. We then reconstruct a prediction of the full returns as a combination of factors considering these disjoint groups of entities and train this ``randomly factorized\" value function as an auxiliary objective for value-based multi-agent reinforcement learning. By doing so, our model can recognize and leverage similarities across tasks to improve learning efficiency in a multi-task setting. Our approach, Randomized Entity-wise Factorization for Imagined Learning (REFIL), outperforms all strong baselines by a significant margin in challenging multi-task StarCraft micromanagement settings.","url_abs":"https://arxiv.org/abs/2006.04222v3","url_pdf":"https://arxiv.org/pdf/2006.04222v3.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":"ai-qmix-attention-and-imagination-for-dynamic","repo_url":"https://github.com/shariqiqbal2810/REFIL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"ai-qmix-attention-and-imagination-for-dynamic","repo_url":"https://github.com/shariqiqbal2810/AI-QMIX","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":"starcraft","task_name":"Starcraft"},{"task_slug":null,"task_name":"counterfactual"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2006.04222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.04222"}},"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/shariqiqbal2810/AI-QMIX","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shariqiqbal2810/REFIL","reach":null}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"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":"a53ab7fcdfd4d3ae","entry":"EntityAttentionFFAgent","repo":"shariqiqbal2810/REFIL","repo_kind":"official","path":"src/modules/agents/entity_ff_agent.py","file_url":"https://github.com/shariqiqbal2810/REFIL/blob/HEAD/src/modules/agents/entity_ff_agent.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":"a53ab7fcdfd4d3ae"}},{"code_sha256_prefix":"d967052a821120c9","entry":"EntityAttentionLayer","repo":"shariqiqbal2810/REFIL","repo_kind":"official","path":"src/modules/agents/entity_ff_agent.py","file_url":"https://github.com/shariqiqbal2810/REFIL/blob/HEAD/src/modules/agents/entity_ff_agent.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":"d967052a821120c9"}},{"code_sha256_prefix":"e411b5be4dfe2aa4","entry":"EntityPoolingLayer","repo":"shariqiqbal2810/REFIL","repo_kind":"official","path":"src/modules/agents/entity_ff_agent.py","file_url":"https://github.com/shariqiqbal2810/REFIL/blob/HEAD/src/modules/agents/entity_ff_agent.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":"e411b5be4dfe2aa4"}},{"code_sha256_prefix":"9469227273fe3ef3","entry":"ImagineEntityAttentionFFAgent","repo":"shariqiqbal2810/REFIL","repo_kind":"official","path":"src/modules/agents/entity_ff_agent.py","file_url":"https://github.com/shariqiqbal2810/REFIL/blob/HEAD/src/modules/agents/entity_ff_agent.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":"9469227273fe3ef3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}