{"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/on-the-interaction-between-supervision-and-1","title":"On the interaction between supervision and self-play in emergent communication","arxiv_id":"2002.01093","date":"2020-02-04","proceeding":"ICLR 2020 1","authors":["Ryan Lowe","Abhinav Gupta","Jakob Foerster","Douwe Kiela","Joelle Pineau"],"abstract":"A promising approach for teaching artificial agents to use natural language involves using human-in-the-loop training. However, recent work suggests that current machine learning methods are too data inefficient to be trained in this way from scratch. In this paper, we investigate the relationship between two categories of learning signals with the ultimate goal of improving sample efficiency: imitating human language data via supervised learning, and maximizing reward in a simulated multi-agent environment via self-play (as done in emergent communication), and introduce the term supervised self-play (S2P) for algorithms using both of these signals. We find that first training agents via supervised learning on human data followed by self-play outperforms the converse, suggesting that it is not beneficial to emerge languages from scratch. We then empirically investigate various S2P schedules that begin with supervised learning in two environments: a Lewis signaling game with symbolic inputs, and an image-based referential game with natural language descriptions. Lastly, we introduce population based approaches to S2P, which further improves the performance over single-agent methods.","url_abs":"https://arxiv.org/abs/2002.01093v2","url_pdf":"https://arxiv.org/pdf/2002.01093v2.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":"on-the-interaction-between-supervision-and-1","repo_url":"https://github.com/backpropper/s2p","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2002.01093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.01093"}},"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/backpropper/s2p","reach":null}],"summary":{"ran":4,"ran_fixture":3,"ran_honours":1,"ran_draft_wrong":3,"unverified":5},"by_repo_kind":{"official":{"samples":16,"ran":11,"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":"7a6f9cb1a39ca0b3","entry":"Beholder","repo":"backpropper/s2p","repo_kind":"official","path":"ibr_game/finetune.py","file_url":"https://github.com/backpropper/s2p/blob/HEAD/ibr_game/finetune.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7a6f9cb1a39ca0b3"}},{"code_sha256_prefix":"9ecb51a47b201507","entry":"Listener","repo":"backpropper/s2p","repo_kind":"official","path":"ibr_game/finetune.py","file_url":"https://github.com/backpropper/s2p/blob/HEAD/ibr_game/finetune.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9ecb51a47b201507"}},{"code_sha256_prefix":"9f509297c82bb3a7","entry":"Speaker","repo":"backpropper/s2p","repo_kind":"official","path":"ibr_game/finetune.py","file_url":"https://github.com/backpropper/s2p/blob/HEAD/ibr_game/finetune.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9f509297c82bb3a7"}},{"code_sha256_prefix":"02b107d78fd0fca7","entry":"filter_caps","repo":"backpropper/s2p","repo_kind":"official","path":"ibr_game/finetune.py","file_url":"https://github.com/backpropper/s2p/blob/HEAD/ibr_game/finetune.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"02b107d78fd0fca7"}},{"code_sha256_prefix":"5a0aaf20a82cf665","entry":"get_s2p_batch","repo":"backpropper/s2p","repo_kind":"official","path":"ibr_game/finetune.py","file_url":"https://github.com/backpropper/s2p/blob/HEAD/ibr_game/finetune.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5a0aaf20a82cf665"}},{"code_sha256_prefix":"779be7e9ddb772f0","entry":"gumbel_softmax","repo":"backpropper/s2p","repo_kind":"official","path":"ibr_game/finetune.py","file_url":"https://github.com/backpropper/s2p/blob/HEAD/ibr_game/finetune.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"779be7e9ddb772f0"}},{"code_sha256_prefix":"626e470a849ef8d9","entry":"gumbel_softmax_sample","repo":"backpropper/s2p","repo_kind":"official","path":"ibr_game/finetune.py","file_url":"https://github.com/backpropper/s2p/blob/HEAD/ibr_game/finetune.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"626e470a849ef8d9"}},{"code_sha256_prefix":"eb35bf807af0e213","entry":"sample_gumbel","repo":"backpropper/s2p","repo_kind":"official","path":"ibr_game/finetune.py","file_url":"https://github.com/backpropper/s2p/blob/HEAD/ibr_game/finetune.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eb35bf807af0e213"}},{"code_sha256_prefix":"7b8ff1df3ed9fbd2","entry":"trim_caps","repo":"backpropper/s2p","repo_kind":"official","path":"ibr_game/finetune.py","file_url":"https://github.com/backpropper/s2p/blob/HEAD/ibr_game/finetune.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7b8ff1df3ed9fbd2"}},{"code_sha256_prefix":"bfdb7c5db11d3441","entry":"truncate_captions","repo":"backpropper/s2p","repo_kind":"official","path":"ibr_game/finetune.py","file_url":"https://github.com/backpropper/s2p/blob/HEAD/ibr_game/finetune.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bfdb7c5db11d3441"}},{"code_sha256_prefix":"d004ca3c465884a6","entry":"truncate_dicts","repo":"backpropper/s2p","repo_kind":"official","path":"ibr_game/finetune.py","file_url":"https://github.com/backpropper/s2p/blob/HEAD/ibr_game/finetune.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d004ca3c465884a6"}},{"code_sha256_prefix":"057dbfd6c2a4131d","entry":"SpeakerListener","repo":"backpropper/s2p","repo_kind":"official","path":"ibr_game/finetune.py","file_url":"https://github.com/backpropper/s2p/blob/HEAD/ibr_game/finetune.py","link_basis":"first_harvest_node","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":"057dbfd6c2a4131d"}},{"code_sha256_prefix":"6509889b8433dd2e","entry":"load_listener","repo":"backpropper/s2p","repo_kind":"official","path":"ibr_game/finetune.py","file_url":"https://github.com/backpropper/s2p/blob/HEAD/ibr_game/finetune.py","link_basis":"first_harvest_node","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":"6509889b8433dd2e"}},{"code_sha256_prefix":"5dffc621e220f31f","entry":"main","repo":"backpropper/s2p","repo_kind":"official","path":"ibr_game/finetune.py","file_url":"https://github.com/backpropper/s2p/blob/HEAD/ibr_game/finetune.py","link_basis":"first_harvest_node","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":"5dffc621e220f31f"}},{"code_sha256_prefix":"975549298f10836c","entry":"save_to_file","repo":"backpropper/s2p","repo_kind":"official","path":"ibr_game/finetune.py","file_url":"https://github.com/backpropper/s2p/blob/HEAD/ibr_game/finetune.py","link_basis":"first_harvest_node","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":"975549298f10836c"}},{"code_sha256_prefix":"409eb80fda6b01b0","entry":"torch_save_to_file","repo":"backpropper/s2p","repo_kind":"official","path":"ibr_game/finetune.py","file_url":"https://github.com/backpropper/s2p/blob/HEAD/ibr_game/finetune.py","link_basis":"first_harvest_node","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":"409eb80fda6b01b0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}