{"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/emergence-of-linguistic-communication-from","title":"Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input","arxiv_id":"1804.03984","date":"2018-04-11","proceeding":"ICLR 2018 1","authors":["Angeliki Lazaridou","Karl Moritz Hermann","Karl Tuyls","Stephen Clark"],"abstract":"The ability of algorithms to evolve or learn (compositional) communication\nprotocols has traditionally been studied in the language evolution literature\nthrough the use of emergent communication tasks. Here we scale up this research\nby using contemporary deep learning methods and by training\nreinforcement-learning neural network agents on referential communication\ngames. We extend previous work, in which agents were trained in symbolic\nenvironments, by developing agents which are able to learn from raw pixel data,\na more challenging and realistic input representation. We find that the degree\nof structure found in the input data affects the nature of the emerged\nprotocols, and thereby corroborate the hypothesis that structured compositional\nlanguage is most likely to emerge when agents perceive the world as being\nstructured.","url_abs":"http://arxiv.org/abs/1804.03984v1","url_pdf":"http://arxiv.org/pdf/1804.03984v1.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":"emergence-of-linguistic-communication-from","repo_url":"https://github.com/nickleomartin/emergent_comm_rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","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":{"syntology_url":"https://syntology.ai/paper/1804.03984","atlas_url":"https://app.syntology.ai/?focus=1804.03984","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.03984"}},"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/nickleomartin/emergent_comm_rl","reach":{"status":"ok","spdx":"MIT"}}],"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":"5ac8a5b08cde956e","entry":"action_distribution","repo":"nickleomartin/emergent_comm_rl","repo_kind":"listed","path":"evaluation.py","file_url":"https://github.com/nickleomartin/emergent_comm_rl/blob/HEAD/evaluation.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":"5ac8a5b08cde956e"}},{"code_sha256_prefix":"94b8d60180371c7b","entry":"levenshtein_message_distance","repo":"nickleomartin/emergent_comm_rl","repo_kind":"listed","path":"evaluation.py","file_url":"https://github.com/nickleomartin/emergent_comm_rl/blob/HEAD/evaluation.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":"94b8d60180371c7b"}},{"code_sha256_prefix":"70f01f07aa8bb12b","entry":"task_accuracy_metrics","repo":"nickleomartin/emergent_comm_rl","repo_kind":"listed","path":"evaluation.py","file_url":"https://github.com/nickleomartin/emergent_comm_rl/blob/HEAD/evaluation.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":"70f01f07aa8bb12b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}