{"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/graph-convolutional-reinforcement-learning","title":"Graph Convolutional Reinforcement Learning","arxiv_id":"1810.09202","date":"2018-10-22","proceeding":"ICLR 2020 1","authors":["Jiechuan Jiang","Chen Dun","Tiejun Huang","Zongqing Lu"],"abstract":"Learning to cooperate is crucially important in multi-agent environments. The key is to understand the mutual interplay between agents. However, multi-agent environments are highly dynamic, where agents keep moving and their neighbors change quickly. This makes it hard to learn abstract representations of mutual interplay between agents. To tackle these difficulties, we propose graph convolutional reinforcement learning, where graph convolution adapts to the dynamics of the underlying graph of the multi-agent environment, and relation kernels capture the interplay between agents by their relation representations. Latent features produced by convolutional layers from gradually increased receptive fields are exploited to learn cooperation, and cooperation is further improved by temporal relation regularization for consistency. Empirically, we show that our method substantially outperforms existing methods in a variety of cooperative scenarios.","url_abs":"https://arxiv.org/abs/1810.09202v5","url_pdf":"https://arxiv.org/pdf/1810.09202v5.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":"graph-convolutional-reinforcement-learning","repo_url":"https://github.com/PKU-AI-Edge/DGN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"graph-convolutional-reinforcement-learning","repo_url":"https://github.com/PKU-AI-Edge/DGN/","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"graph-convolutional-reinforcement-learning","repo_url":"https://github.com/jiechuanjiang/pytorch_dgn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"graph-convolutional-reinforcement-learning","repo_url":"https://github.com/pku-rl/dgn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.09202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.09202"}},"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/PKU-AI-Edge/DGN","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pku-rl/dgn","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jiechuanjiang/pytorch_dgn","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PKU-AI-Edge/DGN/","reach":{"status":"ok"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"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":"f39f2bb84cd0d2ba","entry":"get_obs","repo":"jiechuanjiang/pytorch_dgn","repo_kind":"listed","path":"Starcraft/DGN/utilis.py","file_url":"https://github.com/jiechuanjiang/pytorch_dgn/blob/HEAD/Starcraft/DGN/utilis.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":true,"mcp_get_code":{"code_sha256":"f39f2bb84cd0d2ba"}},{"code_sha256_prefix":"657445ba25ec7e2e","entry":"is_legal","repo":"jiechuanjiang/pytorch_dgn","repo_kind":"listed","path":"Surviving/DGN+ATOC/surviving.py","file_url":"https://github.com/jiechuanjiang/pytorch_dgn/blob/HEAD/Surviving/DGN%2BATOC/surviving.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":true,"mcp_get_code":{"code_sha256":"657445ba25ec7e2e"}},{"code_sha256_prefix":"94c245f3452a240e","entry":"test_agent","repo":"jiechuanjiang/pytorch_dgn","repo_kind":"listed","path":"Starcraft/DGN/utilis.py","file_url":"https://github.com/jiechuanjiang/pytorch_dgn/blob/HEAD/Starcraft/DGN/utilis.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":true,"mcp_get_code":{"code_sha256":"94c245f3452a240e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}