{"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/decstr-learning-goal-directed-abstract","title":"Grounding Language to Autonomously-Acquired Skills via Goal Generation","arxiv_id":"2006.07185","date":"2020-06-12","proceeding":"ICLR 2021 1","authors":["Ahmed Akakzia","Cédric Colas","Pierre-Yves Oudeyer","Mohamed Chetouani","Olivier Sigaud"],"abstract":"We are interested in the autonomous acquisition of repertoires of skills. Language-conditioned reinforcement learning (LC-RL) approaches are great tools in this quest, as they allow to express abstract goals as sets of constraints on the states. However, most LC-RL agents are not autonomous and cannot learn without external instructions and feedback. Besides, their direct language condition cannot account for the goal-directed behavior of pre-verbal infants and strongly limits the expression of behavioral diversity for a given language input. To resolve these issues, we propose a new conceptual approach to language-conditioned RL: the Language-Goal-Behavior architecture (LGB). LGB decouples skill learning and language grounding via an intermediate semantic representation of the world. To showcase the properties of LGB, we present a specific implementation called DECSTR. DECSTR is an intrinsically motivated learning agent endowed with an innate semantic representation describing spatial relations between physical objects. In a first stage (G -> B), it freely explores its environment and targets self-generated semantic configurations. In a second stage (L -> G), it trains a language-conditioned goal generator to generate semantic goals that match the constraints expressed in language-based inputs. We showcase the additional properties of LGB w.r.t. both an end-to-end LC-RL approach and a similar approach leveraging non-semantic, continuous intermediate representations. Intermediate semantic representations help satisfy language commands in a diversity of ways, enable strategy switching after a failure and facilitate language grounding.","url_abs":"https://arxiv.org/abs/2006.07185v3","url_pdf":"https://arxiv.org/pdf/2006.07185v3.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":"decstr-learning-goal-directed-abstract","repo_url":"https://github.com/akakzia/decstr","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"language-acquisition","task_name":"Language Acquisition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.07185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.07185"}},"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/akakzia/decstr","reach":null}],"summary":{"ran":9,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":12,"ran":10,"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":12,"samples":[{"code_sha256_prefix":"d8e31ae3112e4d80","entry":"LanguageActor","repo":"akakzia/decstr","repo_kind":"official","path":"rl_modules/language_models.py","file_url":"https://github.com/akakzia/decstr/blob/HEAD/rl_modules/language_models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d8e31ae3112e4d80"}},{"code_sha256_prefix":"c39bf0f097ab50b4","entry":"LanguageCritic","repo":"akakzia/decstr","repo_kind":"official","path":"rl_modules/language_models.py","file_url":"https://github.com/akakzia/decstr/blob/HEAD/rl_modules/language_models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c39bf0f097ab50b4"}},{"code_sha256_prefix":"a9b0c69825ca0932","entry":"OneHotEncoder","repo":"akakzia/decstr","repo_kind":"official","path":"rl_modules/language_models.py","file_url":"https://github.com/akakzia/decstr/blob/HEAD/rl_modules/language_models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a9b0c69825ca0932"}},{"code_sha256_prefix":"f90e167334ba7d25","entry":"PhiActorDeepSet","repo":"akakzia/decstr","repo_kind":"official","path":"rl_modules/language_models.py","file_url":"https://github.com/akakzia/decstr/blob/HEAD/rl_modules/language_models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f90e167334ba7d25"}},{"code_sha256_prefix":"a0c7a79e96131b44","entry":"PhiCriticDeepSet","repo":"akakzia/decstr","repo_kind":"official","path":"rl_modules/language_models.py","file_url":"https://github.com/akakzia/decstr/blob/HEAD/rl_modules/language_models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a0c7a79e96131b44"}},{"code_sha256_prefix":"ccc6f7bb4da61ebf","entry":"RhoActorDeepSet","repo":"akakzia/decstr","repo_kind":"official","path":"rl_modules/language_models.py","file_url":"https://github.com/akakzia/decstr/blob/HEAD/rl_modules/language_models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ccc6f7bb4da61ebf"}},{"code_sha256_prefix":"56e898d6b7d33800","entry":"RhoCriticDeepSet","repo":"akakzia/decstr","repo_kind":"official","path":"rl_modules/language_models.py","file_url":"https://github.com/akakzia/decstr/blob/HEAD/rl_modules/language_models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"56e898d6b7d33800"}},{"code_sha256_prefix":"9d57a15e8984f921","entry":"Vocab","repo":"akakzia/decstr","repo_kind":"official","path":"rl_modules/language_models.py","file_url":"https://github.com/akakzia/decstr/blob/HEAD/rl_modules/language_models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9d57a15e8984f921"}},{"code_sha256_prefix":"4599803538ea8c09","entry":"analyze_inst","repo":"akakzia/decstr","repo_kind":"official","path":"rl_modules/language_models.py","file_url":"https://github.com/akakzia/decstr/blob/HEAD/rl_modules/language_models.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":"4599803538ea8c09"}},{"code_sha256_prefix":"52528acbf7b146d7","entry":"get_instruction","repo":"akakzia/decstr","repo_kind":"official","path":"rl_modules/language_models.py","file_url":"https://github.com/akakzia/decstr/blob/HEAD/rl_modules/language_models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"52528acbf7b146d7"}},{"code_sha256_prefix":"0561dfa9303b9099","entry":"AbstractEncoder","repo":"akakzia/decstr","repo_kind":"official","path":"rl_modules/language_models.py","file_url":"https://github.com/akakzia/decstr/blob/HEAD/rl_modules/language_models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0561dfa9303b9099"}},{"code_sha256_prefix":"7ab22d95fba183e7","entry":"DeepSetLanguage","repo":"akakzia/decstr","repo_kind":"official","path":"rl_modules/language_models.py","file_url":"https://github.com/akakzia/decstr/blob/HEAD/rl_modules/language_models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7ab22d95fba183e7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}