{"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/relational-deep-reinforcement-learning","title":"Relational Deep Reinforcement Learning","arxiv_id":"1806.01830","date":"2018-06-05","proceeding":null,"authors":["Vinicius Zambaldi","David Raposo","Adam Santoro","Victor Bapst","Yujia Li","Igor Babuschkin","Karl Tuyls","David Reichert","Timothy Lillicrap","Edward Lockhart","Murray Shanahan","Victoria Langston","Razvan Pascanu","Matthew Botvinick","Oriol Vinyals","Peter Battaglia"],"abstract":"We introduce an approach for deep reinforcement learning (RL) that improves\nupon the efficiency, generalization capacity, and interpretability of\nconventional approaches through structured perception and relational reasoning.\nIt uses self-attention to iteratively reason about the relations between\nentities in a scene and to guide a model-free policy. Our results show that in\na novel navigation and planning task called Box-World, our agent finds\ninterpretable solutions that improve upon baselines in terms of sample\ncomplexity, ability to generalize to more complex scenes than experienced\nduring training, and overall performance. In the StarCraft II Learning\nEnvironment, our agent achieves state-of-the-art performance on six mini-games\n-- surpassing human grandmaster performance on four. By considering\narchitectural inductive biases, our work opens new directions for overcoming\nimportant, but stubborn, challenges in deep RL.","url_abs":"http://arxiv.org/abs/1806.01830v2","url_pdf":"http://arxiv.org/pdf/1806.01830v2.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":"relational-deep-reinforcement-learning","repo_url":"https://github.com/inoryy/reaver","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"relational-deep-reinforcement-learning","repo_url":"https://github.com/mavischer/DRRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"relational-deep-reinforcement-learning","repo_url":"https://github.com/nathangrinsztajn/Box-World","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"relational-deep-reinforcement-learning","repo_url":"https://github.com/nathanin/pad","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"relational-deep-reinforcement-learning","repo_url":"https://github.com/nicoladainese96/RelationalDeepRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"relational-deep-reinforcement-learning","repo_url":"https://github.com/nicoladainese96/SC2-RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"relational-deep-reinforcement-learning","repo_url":"https://github.com/Liberty3000/rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"relational-reasoning","task_name":"Relational Reasoning"},{"task_slug":"starcraft","task_name":"Starcraft"},{"task_slug":"starcraft-ii","task_name":"Starcraft II"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"interpretability","method_name":"Interpretability"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.01830","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.01830"}},"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/nicoladainese96/SC2-RL","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mavischer/DRRL","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Liberty3000/rl","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nicoladainese96/RelationalDeepRL","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nathanin/pad","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/inoryy/reaver","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nathangrinsztajn/Box-World","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":4,"unverified":4},"by_repo_kind":{"listed":{"samples":8,"ran":4,"repositories":3}},"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":4,"samples":[{"code_sha256_prefix":"2271c8526c9dce4e","entry":"clones","repo":"nicoladainese96/RelationalDeepRL","repo_kind":"listed","path":"RelationalModule/RelationalNetworks.py","file_url":"https://github.com/nicoladainese96/RelationalDeepRL/blob/HEAD/RelationalModule/RelationalNetworks.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2271c8526c9dce4e"}},{"code_sha256_prefix":"2eacb54e050a89ca","entry":"get_color_dict","repo":"nicoladainese96/RelationalDeepRL","repo_kind":"listed","path":"Utils/train_agent.py","file_url":"https://github.com/nicoladainese96/RelationalDeepRL/blob/HEAD/Utils/train_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2eacb54e050a89ca"}},{"code_sha256_prefix":"2840e9977435e9ff","entry":"get_state","repo":"nicoladainese96/RelationalDeepRL","repo_kind":"listed","path":"Utils/train_agent.py","file_url":"https://github.com/nicoladainese96/RelationalDeepRL/blob/HEAD/Utils/train_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2840e9977435e9ff"}},{"code_sha256_prefix":"5e5f7cfb6e59e9fe","entry":"play_episode","repo":"nicoladainese96/RelationalDeepRL","repo_kind":"listed","path":"Utils/train_agent.py","file_url":"https://github.com/nicoladainese96/RelationalDeepRL/blob/HEAD/Utils/train_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5e5f7cfb6e59e9fe"}},{"code_sha256_prefix":"1370fecfbea0eb23","entry":"is_empty","repo":"nathangrinsztajn/Box-World","repo_kind":"listed","path":"boxworld_gen.py","file_url":"https://github.com/nathangrinsztajn/Box-World/blob/HEAD/boxworld_gen.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":"1370fecfbea0eb23"}},{"code_sha256_prefix":"c9c02de53f161dbb","entry":"parse","repo":"inoryy/reaver","repo_kind":"listed","path":"reaver/envs/gym.py","file_url":"https://github.com/inoryy/reaver/blob/HEAD/reaver/envs/gym.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":"c9c02de53f161dbb"}},{"code_sha256_prefix":"13b1a016d3def745","entry":"sampling_pairs","repo":"nathangrinsztajn/Box-World","repo_kind":"listed","path":"boxworld_gen.py","file_url":"https://github.com/nathangrinsztajn/Box-World/blob/HEAD/boxworld_gen.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":"13b1a016d3def745"}},{"code_sha256_prefix":"042e8679c9d88ed2","entry":"world_gen","repo":"nathangrinsztajn/Box-World","repo_kind":"listed","path":"boxworld_gen.py","file_url":"https://github.com/nathangrinsztajn/Box-World/blob/HEAD/boxworld_gen.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":"042e8679c9d88ed2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}