{"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/learning-cooperative-visual-dialog-agents","title":"Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning","arxiv_id":"1703.06585","date":"2017-03-20","proceeding":"ICCV 2017 10","authors":["Abhishek Das","Satwik Kottur","José M. F. Moura","Stefan Lee","Dhruv Batra"],"abstract":"We introduce the first goal-driven training for visual question answering and\ndialog agents. Specifically, we pose a cooperative 'image guessing' game\nbetween two agents -- Qbot and Abot -- who communicate in natural language\ndialog so that Qbot can select an unseen image from a lineup of images. We use\ndeep reinforcement learning (RL) to learn the policies of these agents\nend-to-end -- from pixels to multi-agent multi-round dialog to game reward.\n  We demonstrate two experimental results.\n  First, as a 'sanity check' demonstration of pure RL (from scratch), we show\nresults on a synthetic world, where the agents communicate in ungrounded\nvocabulary, i.e., symbols with no pre-specified meanings (X, Y, Z). We find\nthat two bots invent their own communication protocol and start using certain\nsymbols to ask/answer about certain visual attributes (shape/color/style).\nThus, we demonstrate the emergence of grounded language and communication among\n'visual' dialog agents with no human supervision.\n  Second, we conduct large-scale real-image experiments on the VisDial dataset,\nwhere we pretrain with supervised dialog data and show that the RL 'fine-tuned'\nagents significantly outperform SL agents. Interestingly, the RL Qbot learns to\nask questions that Abot is good at, ultimately resulting in more informative\ndialog and a better team.","url_abs":"http://arxiv.org/abs/1703.06585v2","url_pdf":"http://arxiv.org/pdf/1703.06585v2.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":"learning-cooperative-visual-dialog-agents","repo_url":"https://github.com/Cremiy/visdial-rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-cooperative-visual-dialog-agents","repo_url":"https://github.com/batra-mlp-lab/visdial-rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-cooperative-visual-dialog-agents","repo_url":"https://github.com/kdexd/lang-emerge-parlai","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-cooperative-visual-dialog-agents","repo_url":"https://github.com/naver/aqm-plus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-cooperative-visual-dialog-agents","repo_url":"https://github.com/sea-snell/implicit-language-q-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-cooperative-visual-dialog-agents","repo_url":"https://github.com/vmurahari3/visdial-diversity","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-cooperative-visual-dialog-agents","repo_url":"https://github.com/zilongzheng/visdial-gnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"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":"visual-dialogue","task_name":"Visual Dialog"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1703.06585","atlas_url":"https://app.syntology.ai/?focus=1703.06585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.06585"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/kdexd/lang-emerge-parlai","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/naver/aqm-plus","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/batra-mlp-lab/visdial-rl","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vmurahari3/visdial-diversity","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sea-snell/implicit-language-q-learning","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zilongzheng/visdial-gnn","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Cremiy/visdial-rl","reach":{"status":"ok"}}],"summary":{"ran":1,"ran_honours":1,"ran_fixture":1,"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":4,"ran":4,"repositories":2}},"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":1,"samples":[{"code_sha256_prefix":"28c42aa5a85d3383","entry":"getRandomQuestions","repo":"naver/aqm-plus","repo_kind":"listed","path":"eval_utils/aqm_runner.py","file_url":"https://github.com/naver/aqm-plus/blob/HEAD/eval_utils/aqm_runner.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"28c42aa5a85d3383"}},{"code_sha256_prefix":"b38c7aecbb3887ef","entry":"getRank","repo":"naver/aqm-plus","repo_kind":"listed","path":"eval_utils/aqm_runner.py","file_url":"https://github.com/naver/aqm-plus/blob/HEAD/eval_utils/aqm_runner.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b38c7aecbb3887ef"}},{"code_sha256_prefix":"d9f167cab121e616","entry":"normProb","repo":"naver/aqm-plus","repo_kind":"listed","path":"eval_utils/aqm_runner.py","file_url":"https://github.com/naver/aqm-plus/blob/HEAD/eval_utils/aqm_runner.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"d9f167cab121e616"}},{"code_sha256_prefix":"daf2dbf91f9be1cd","entry":"xavier_init","repo":"kdexd/lang-emerge-parlai","repo_kind":"listed","path":"bots.py","file_url":"https://github.com/kdexd/lang-emerge-parlai/blob/HEAD/bots.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":"daf2dbf91f9be1cd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}