{"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/influence-based-multi-agent-exploration","title":"Influence-Based Multi-Agent Exploration","arxiv_id":"1910.05512","date":"2019-10-12","proceeding":"ICLR 2020 1","authors":["Tonghan Wang","Jianhao Wang","Yi Wu","Chongjie Zhang"],"abstract":"Intrinsically motivated reinforcement learning aims to address the exploration challenge for sparse-reward tasks. However, the study of exploration methods in transition-dependent multi-agent settings is largely absent from the literature. We aim to take a step towards solving this problem. We present two exploration methods: exploration via information-theoretic influence (EITI) and exploration via decision-theoretic influence (EDTI), by exploiting the role of interaction in coordinated behaviors of agents. EITI uses mutual information to capture influence transition dynamics. EDTI uses a novel intrinsic reward, called Value of Interaction (VoI), to characterize and quantify the influence of one agent's behavior on expected returns of other agents. By optimizing EITI or EDTI objective as a regularizer, agents are encouraged to coordinate their exploration and learn policies to optimize team performance. We show how to optimize these regularizers so that they can be easily integrated with policy gradient reinforcement learning. The resulting update rule draws a connection between coordinated exploration and intrinsic reward distribution. Finally, we empirically demonstrate the significant strength of our method in a variety of multi-agent scenarios.","url_abs":"https://arxiv.org/abs/1910.05512v1","url_pdf":"https://arxiv.org/pdf/1910.05512v1.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":"influence-based-multi-agent-exploration","repo_url":"https://github.com/TonghanWang/EITI-EDTI","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"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":{"atlas_url":"https://app.syntology.ai/?focus=1910.05512","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.05512"}},"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/TonghanWang/EITI-EDTI","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":7,"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":7,"samples":[{"code_sha256_prefix":"a44574392d168384","entry":"register","repo":"TonghanWang/EITI-EDTI","repo_kind":"official","path":"baselines/common/models.py","file_url":"https://github.com/TonghanWang/EITI-EDTI/blob/HEAD/baselines/common/models.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"a44574392d168384"}},{"code_sha256_prefix":"4bae0064832da0e2","entry":"add_shape","repo":"TonghanWang/EITI-EDTI","repo_kind":"official","path":"baselines/Curiosity.py","file_url":"https://github.com/TonghanWang/EITI-EDTI/blob/HEAD/baselines/Curiosity.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":false,"mcp_get_code":{"code_sha256":"4bae0064832da0e2"}},{"code_sha256_prefix":"817d5caf0e3d3706","entry":"make_output_format","repo":"TonghanWang/EITI-EDTI","repo_kind":"official","path":"baselines/logger.py","file_url":"https://github.com/TonghanWang/EITI-EDTI/blob/HEAD/baselines/logger.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":false,"mcp_get_code":{"code_sha256":"817d5caf0e3d3706"}},{"code_sha256_prefix":"8880b5d743b619cf","entry":"mk","repo":"TonghanWang/EITI-EDTI","repo_kind":"official","path":"baselines/Curiosity.py","file_url":"https://github.com/TonghanWang/EITI-EDTI/blob/HEAD/baselines/Curiosity.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":false,"mcp_get_code":{"code_sha256":"8880b5d743b619cf"}},{"code_sha256_prefix":"5d25665155d8e220","entry":"mk1","repo":"TonghanWang/EITI-EDTI","repo_kind":"official","path":"baselines/Curiosity.py","file_url":"https://github.com/TonghanWang/EITI-EDTI/blob/HEAD/baselines/Curiosity.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":false,"mcp_get_code":{"code_sha256":"5d25665155d8e220"}},{"code_sha256_prefix":"8455885a0d199802","entry":"profile","repo":"TonghanWang/EITI-EDTI","repo_kind":"official","path":"baselines/logger.py","file_url":"https://github.com/TonghanWang/EITI-EDTI/blob/HEAD/baselines/logger.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":false,"mcp_get_code":{"code_sha256":"8455885a0d199802"}},{"code_sha256_prefix":"88ef5a17fc986d9a","entry":"read_json","repo":"TonghanWang/EITI-EDTI","repo_kind":"official","path":"baselines/logger.py","file_url":"https://github.com/TonghanWang/EITI-EDTI/blob/HEAD/baselines/logger.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":false,"mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}