{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KCFYQEM274JVFSY7FGSPN4MAXX","short_pith_number":"pith:KCFYQEM2","schema_version":"1.0","canonical_sha256":"508b88119aff1352cb1f29a4f6f180bdfb675e67eef4441e10e6d0611affccf0","source":{"kind":"arxiv","id":"2309.11564","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical reinforcement learning with natural language subgoals","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Arun Ahuja, Ishita Dasgupta, Kavya Kopparapu, Rob Fergus","submitted_at":"2023-09-20T18:03:04Z","abstract_excerpt":"Hierarchical reinforcement learning has been a compelling approach for achieving goal directed behavior over long sequences of actions. However, it has been challenging to implement in realistic or open-ended environments. A main challenge has been to find the right space of sub-goals over which to instantiate a hierarchy. We present a novel approach where we use data from humans solving these tasks to softly supervise the goal space for a set of long range tasks in a 3D embodied environment. In particular, we use unconstrained natural language to parameterize this space. This has two advantag"},"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":"2309.11564","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-20T18:03:04Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5ed5dfff3c6f47b30085bed11fd1222528dc070c94bdd82a5e937ea48a0b0fcb","abstract_canon_sha256":"e18eaa1e59c35f4e43003f5bdf5e4faa401443c38490b8325b5f8376bd4abd72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:51.656220Z","signature_b64":"DiKENQUD63hfzxWIDzXS7W9jxMhqlJ5l8im/WFz1x1OCmHweKVI1djyO4z0jG9Rb97e1jZpj1glCq7gT3bI6DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"508b88119aff1352cb1f29a4f6f180bdfb675e67eef4441e10e6d0611affccf0","last_reissued_at":"2026-07-05T06:52:51.655746Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:51.655746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical reinforcement learning with natural language subgoals","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Arun Ahuja, Ishita Dasgupta, Kavya Kopparapu, Rob Fergus","submitted_at":"2023-09-20T18:03:04Z","abstract_excerpt":"Hierarchical reinforcement learning has been a compelling approach for achieving goal directed behavior over long sequences of actions. However, it has been challenging to implement in realistic or open-ended environments. A main challenge has been to find the right space of sub-goals over which to instantiate a hierarchy. We present a novel approach where we use data from humans solving these tasks to softly supervise the goal space for a set of long range tasks in a 3D embodied environment. In particular, we use unconstrained natural language to parameterize this space. This has two advantag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11564","kind":"arxiv","version":1},"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/2309.11564/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":"2309.11564","created_at":"2026-07-05T06:52:51.655805+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.11564v1","created_at":"2026-07-05T06:52:51.655805+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11564","created_at":"2026-07-05T06:52:51.655805+00:00"},{"alias_kind":"pith_short_12","alias_value":"KCFYQEM274JV","created_at":"2026-07-05T06:52:51.655805+00:00"},{"alias_kind":"pith_short_16","alias_value":"KCFYQEM274JVFSY7","created_at":"2026-07-05T06:52:51.655805+00:00"},{"alias_kind":"pith_short_8","alias_value":"KCFYQEM2","created_at":"2026-07-05T06:52:51.655805+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.14751","citing_title":"HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KCFYQEM274JVFSY7FGSPN4MAXX","json":"https://pith.science/pith/KCFYQEM274JVFSY7FGSPN4MAXX.json","graph_json":"https://pith.science/api/pith-number/KCFYQEM274JVFSY7FGSPN4MAXX/graph.json","events_json":"https://pith.science/api/pith-number/KCFYQEM274JVFSY7FGSPN4MAXX/events.json","paper":"https://pith.science/paper/KCFYQEM2"},"agent_actions":{"view_html":"https://pith.science/pith/KCFYQEM274JVFSY7FGSPN4MAXX","download_json":"https://pith.science/pith/KCFYQEM274JVFSY7FGSPN4MAXX.json","view_paper":"https://pith.science/paper/KCFYQEM2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.11564&json=true","fetch_graph":"https://pith.science/api/pith-number/KCFYQEM274JVFSY7FGSPN4MAXX/graph.json","fetch_events":"https://pith.science/api/pith-number/KCFYQEM274JVFSY7FGSPN4MAXX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KCFYQEM274JVFSY7FGSPN4MAXX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KCFYQEM274JVFSY7FGSPN4MAXX/action/storage_attestation","attest_author":"https://pith.science/pith/KCFYQEM274JVFSY7FGSPN4MAXX/action/author_attestation","sign_citation":"https://pith.science/pith/KCFYQEM274JVFSY7FGSPN4MAXX/action/citation_signature","submit_replication":"https://pith.science/pith/KCFYQEM274JVFSY7FGSPN4MAXX/action/replication_record"}},"created_at":"2026-07-05T06:52:51.655805+00:00","updated_at":"2026-07-05T06:52:51.655805+00:00"}