{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FWOGCTWNWCICYKNNW3D4FLUIHW","short_pith_number":"pith:FWOGCTWN","schema_version":"1.0","canonical_sha256":"2d9c614ecdb0902c29adb6c7c2ae883dbee638b4d556b1b5b83a3a1c83308160","source":{"kind":"arxiv","id":"2006.07185","version":3},"attestation_state":"computed","paper":{"title":"Grounding Language to Autonomously-Acquired Skills via Goal Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Ahmed Akakzia, C\\'edric Colas, Mohamed Chetouani, Olivier Sigaud, Pierre-Yves Oudeyer","submitted_at":"2020-06-12T13:46:10Z","abstract_excerpt":"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 conceptua"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2006.07185","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-06-12T13:46:10Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"9df48653d3cf636904077f7c7c1eb8f7fdb734b52087e7aa19e21655768c99bb","abstract_canon_sha256":"0b32fd779e28ecace1c086205231cd749334519ed722fdf75b8fd022aca8b892"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:09:10.877060Z","signature_b64":"bsLhtpkAk3tdJMXuVK++akcMFNeIFQ5wp2Oi4Gg9QdNTI3n2BOsM2lm07WxsW9/llvSrswlfD72kNAVwDFgUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d9c614ecdb0902c29adb6c7c2ae883dbee638b4d556b1b5b83a3a1c83308160","last_reissued_at":"2026-07-05T02:09:10.876688Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:09:10.876688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grounding Language to Autonomously-Acquired Skills via Goal Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Ahmed Akakzia, C\\'edric Colas, Mohamed Chetouani, Olivier Sigaud, Pierre-Yves Oudeyer","submitted_at":"2020-06-12T13:46:10Z","abstract_excerpt":"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 conceptua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07185","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.07185/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2006.07185","created_at":"2026-07-05T02:09:10.876744+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.07185v3","created_at":"2026-07-05T02:09:10.876744+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07185","created_at":"2026-07-05T02:09:10.876744+00:00"},{"alias_kind":"pith_short_12","alias_value":"FWOGCTWNWCIC","created_at":"2026-07-05T02:09:10.876744+00:00"},{"alias_kind":"pith_short_16","alias_value":"FWOGCTWNWCICYKNN","created_at":"2026-07-05T02:09:10.876744+00:00"},{"alias_kind":"pith_short_8","alias_value":"FWOGCTWN","created_at":"2026-07-05T02:09:10.876744+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22488","citing_title":"SCOPE: Evolving Symbolic World for Planning in Open-Ended Environments","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2209.07753","citing_title":"Code as Policies: Language Model Programs for Embodied Control","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01862","citing_title":"QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2204.01691","citing_title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FWOGCTWNWCICYKNNW3D4FLUIHW","json":"https://pith.science/pith/FWOGCTWNWCICYKNNW3D4FLUIHW.json","graph_json":"https://pith.science/api/pith-number/FWOGCTWNWCICYKNNW3D4FLUIHW/graph.json","events_json":"https://pith.science/api/pith-number/FWOGCTWNWCICYKNNW3D4FLUIHW/events.json","paper":"https://pith.science/paper/FWOGCTWN"},"agent_actions":{"view_html":"https://pith.science/pith/FWOGCTWNWCICYKNNW3D4FLUIHW","download_json":"https://pith.science/pith/FWOGCTWNWCICYKNNW3D4FLUIHW.json","view_paper":"https://pith.science/paper/FWOGCTWN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.07185&json=true","fetch_graph":"https://pith.science/api/pith-number/FWOGCTWNWCICYKNNW3D4FLUIHW/graph.json","fetch_events":"https://pith.science/api/pith-number/FWOGCTWNWCICYKNNW3D4FLUIHW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FWOGCTWNWCICYKNNW3D4FLUIHW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FWOGCTWNWCICYKNNW3D4FLUIHW/action/storage_attestation","attest_author":"https://pith.science/pith/FWOGCTWNWCICYKNNW3D4FLUIHW/action/author_attestation","sign_citation":"https://pith.science/pith/FWOGCTWNWCICYKNNW3D4FLUIHW/action/citation_signature","submit_replication":"https://pith.science/pith/FWOGCTWNWCICYKNNW3D4FLUIHW/action/replication_record"}},"created_at":"2026-07-05T02:09:10.876744+00:00","updated_at":"2026-07-05T02:09:10.876744+00:00"}