{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KCFYQEM274JVFSY7FGSPN4MAXX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e18eaa1e59c35f4e43003f5bdf5e4faa401443c38490b8325b5f8376bd4abd72","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-20T18:03:04Z","title_canon_sha256":"5ed5dfff3c6f47b30085bed11fd1222528dc070c94bdd82a5e937ea48a0b0fcb"},"schema_version":"1.0","source":{"id":"2309.11564","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.11564","created_at":"2026-07-05T06:52:51Z"},{"alias_kind":"arxiv_version","alias_value":"2309.11564v1","created_at":"2026-07-05T06:52:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11564","created_at":"2026-07-05T06:52:51Z"},{"alias_kind":"pith_short_12","alias_value":"KCFYQEM274JV","created_at":"2026-07-05T06:52:51Z"},{"alias_kind":"pith_short_16","alias_value":"KCFYQEM274JVFSY7","created_at":"2026-07-05T06:52:51Z"},{"alias_kind":"pith_short_8","alias_value":"KCFYQEM2","created_at":"2026-07-05T06:52:51Z"}],"graph_snapshots":[{"event_id":"sha256:cf1d33da58f2bf2aedbc9ca824d663825525dfd8c64f80bf9a658e753f4e760b","target":"graph","created_at":"2026-07-05T06:52:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2309.11564/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Arun Ahuja, Ishita Dasgupta, Kavya Kopparapu, Rob Fergus","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-20T18:03:04Z","title":"Hierarchical reinforcement learning with natural language subgoals"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11564","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5ec47aced473758991b0059bb5209b3caf222a0637e4a797df3f1f3ef934df99","target":"record","created_at":"2026-07-05T06:52:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e18eaa1e59c35f4e43003f5bdf5e4faa401443c38490b8325b5f8376bd4abd72","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-20T18:03:04Z","title_canon_sha256":"5ed5dfff3c6f47b30085bed11fd1222528dc070c94bdd82a5e937ea48a0b0fcb"},"schema_version":"1.0","source":{"id":"2309.11564","kind":"arxiv","version":1}},"canonical_sha256":"508b88119aff1352cb1f29a4f6f180bdfb675e67eef4441e10e6d0611affccf0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"508b88119aff1352cb1f29a4f6f180bdfb675e67eef4441e10e6d0611affccf0","first_computed_at":"2026-07-05T06:52:51.655746Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:52:51.655746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DiKENQUD63hfzxWIDzXS7W9jxMhqlJ5l8im/WFz1x1OCmHweKVI1djyO4z0jG9Rb97e1jZpj1glCq7gT3bI6DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:52:51.656220Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.11564","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ec47aced473758991b0059bb5209b3caf222a0637e4a797df3f1f3ef934df99","sha256:cf1d33da58f2bf2aedbc9ca824d663825525dfd8c64f80bf9a658e753f4e760b"],"state_sha256":"7bb8fbafa509330d8d17cf9545c906e0d852805474b442eb6fb1bacb4dfe494f"}