{"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/deep-multi-agent-reinforcement-learning-with","title":"Deep Multi-Agent Reinforcement Learning with Relevance Graphs","arxiv_id":"1811.12557","date":"2018-11-30","proceeding":null,"authors":["Aleksandra Malysheva","Tegg Taekyong Sung","Chae-Bong Sohn","Daniel Kudenko","Aleksei Shpilman"],"abstract":"Over recent years, deep reinforcement learning has shown strong successes in\ncomplex single-agent tasks, and more recently this approach has also been\napplied to multi-agent domains. In this paper, we propose a novel approach,\ncalled MAGnet, to multi-agent reinforcement learning (MARL) that utilizes a\nrelevance graph representation of the environment obtained by a self-attention\nmechanism, and a message-generation technique inspired by the NerveNet\narchitecture. We applied our MAGnet approach to the Pommerman game and the\nresults show that it significantly outperforms state-of-the-art MARL solutions,\nincluding DQN, MADDPG, and MCTS.","url_abs":"http://arxiv.org/abs/1811.12557v1","url_pdf":"http://arxiv.org/pdf/1811.12557v1.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":"deep-multi-agent-reinforcement-learning-with","repo_url":"https://github.com/tegg89/magnet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"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":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dqn","method_name":"DQN"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"experience-replay","method_name":"Experience Replay"},{"method_slug":"maddpg","method_name":"MADDPG"},{"method_slug":"q-learning","method_name":"Q-Learning"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.12557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.12557"}},"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/tegg89/magnet","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"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":"930b524d6b021ed1","entry":"batch_norm","repo":"tegg89/magnet","repo_kind":"official","path":"models/action_execution/actor_critic_nn.py","file_url":"https://github.com/tegg89/magnet/blob/HEAD/models/action_execution/actor_critic_nn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"930b524d6b021ed1"}},{"code_sha256_prefix":"c04864a6841339e7","entry":"check_next_to_bomb","repo":"tegg89/magnet","repo_kind":"official","path":"env_processing/shaping.py","file_url":"https://github.com/tegg89/magnet/blob/HEAD/env_processing/shaping.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c04864a6841339e7"}},{"code_sha256_prefix":"e95e6dd3a35646ba","entry":"discretize","repo":"tegg89/magnet","repo_kind":"official","path":"models/action_execution/actor_critic_nn.py","file_url":"https://github.com/tegg89/magnet/blob/HEAD/models/action_execution/actor_critic_nn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e95e6dd3a35646ba"}},{"code_sha256_prefix":"d108d1b5ff426750","entry":"init_list_of_vertex","repo":"tegg89/magnet","repo_kind":"official","path":"env_processing/shaping.py","file_url":"https://github.com/tegg89/magnet/blob/HEAD/env_processing/shaping.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d108d1b5ff426750"}},{"code_sha256_prefix":"8e9ed77aca673ea4","entry":"model_NN1","repo":"tegg89/magnet","repo_kind":"official","path":"models/graph_construction/NN1.py","file_url":"https://github.com/tegg89/magnet/blob/HEAD/models/graph_construction/NN1.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8e9ed77aca673ea4"}},{"code_sha256_prefix":"13e0cdee9d418dbc","entry":"model_NN2","repo":"tegg89/magnet","repo_kind":"official","path":"models/action_execution/NN2.py","file_url":"https://github.com/tegg89/magnet/blob/HEAD/models/action_execution/NN2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"13e0cdee9d418dbc"}},{"code_sha256_prefix":"093c23bdbb785c8a","entry":"reward_shaping","repo":"tegg89/magnet","repo_kind":"official","path":"env_processing/shaping.py","file_url":"https://github.com/tegg89/magnet/blob/HEAD/env_processing/shaping.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"093c23bdbb785c8a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}