{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UTIV7QROW36P45BMNBNMXGZILM","short_pith_number":"pith:UTIV7QRO","schema_version":"1.0","canonical_sha256":"a4d15fc22eb6fcfe742c685acb9b285b2bde2ab0bee1d4339a99bcf524c996fb","source":{"kind":"arxiv","id":"2111.09858","version":1},"attestation_state":"computed","paper":{"title":"Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Christopher Hoang, Honglak Lee, Jongwook Choi, Sungryull Sohn, Wilka Carvalho","submitted_at":"2021-11-18T18:36:05Z","abstract_excerpt":"Operating in the real-world often requires agents to learn about a complex environment and apply this understanding to achieve a breadth of goals. This problem, known as goal-conditioned reinforcement learning (GCRL), becomes especially challenging for long-horizon goals. Current methods have tackled this problem by augmenting goal-conditioned policies with graph-based planning algorithms. However, they struggle to scale to large, high-dimensional state spaces and assume access to exploration mechanisms for efficiently collecting training data. In this work, we introduce Successor Feature Land"},"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":"2111.09858","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-18T18:36:05Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"title_canon_sha256":"69ea731d9af6849a4cb974fc9092bdd0a2d888477b038da91ff35c9ff6150a48","abstract_canon_sha256":"de84474de3a2d5446b5e0132e4caf38fba38806a0825d7dbc4882fc0f977af54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:33:16.396453Z","signature_b64":"pU138LsehqISxzqyP6c71NJWD7CLYNUfUNCYVgnenZBWjRN48sieAer/kZNeei+u5UVe/2wFhW66rUM4w0p+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4d15fc22eb6fcfe742c685acb9b285b2bde2ab0bee1d4339a99bcf524c996fb","last_reissued_at":"2026-07-05T03:33:16.396018Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:33:16.396018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Christopher Hoang, Honglak Lee, Jongwook Choi, Sungryull Sohn, Wilka Carvalho","submitted_at":"2021-11-18T18:36:05Z","abstract_excerpt":"Operating in the real-world often requires agents to learn about a complex environment and apply this understanding to achieve a breadth of goals. This problem, known as goal-conditioned reinforcement learning (GCRL), becomes especially challenging for long-horizon goals. Current methods have tackled this problem by augmenting goal-conditioned policies with graph-based planning algorithms. However, they struggle to scale to large, high-dimensional state spaces and assume access to exploration mechanisms for efficiently collecting training data. In this work, we introduce Successor Feature Land"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.09858","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/2111.09858/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":"2111.09858","created_at":"2026-07-05T03:33:16.396079+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.09858v1","created_at":"2026-07-05T03:33:16.396079+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.09858","created_at":"2026-07-05T03:33:16.396079+00:00"},{"alias_kind":"pith_short_12","alias_value":"UTIV7QROW36P","created_at":"2026-07-05T03:33:16.396079+00:00"},{"alias_kind":"pith_short_16","alias_value":"UTIV7QROW36P45BM","created_at":"2026-07-05T03:33:16.396079+00:00"},{"alias_kind":"pith_short_8","alias_value":"UTIV7QRO","created_at":"2026-07-05T03:33:16.396079+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UTIV7QROW36P45BMNBNMXGZILM","json":"https://pith.science/pith/UTIV7QROW36P45BMNBNMXGZILM.json","graph_json":"https://pith.science/api/pith-number/UTIV7QROW36P45BMNBNMXGZILM/graph.json","events_json":"https://pith.science/api/pith-number/UTIV7QROW36P45BMNBNMXGZILM/events.json","paper":"https://pith.science/paper/UTIV7QRO"},"agent_actions":{"view_html":"https://pith.science/pith/UTIV7QROW36P45BMNBNMXGZILM","download_json":"https://pith.science/pith/UTIV7QROW36P45BMNBNMXGZILM.json","view_paper":"https://pith.science/paper/UTIV7QRO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.09858&json=true","fetch_graph":"https://pith.science/api/pith-number/UTIV7QROW36P45BMNBNMXGZILM/graph.json","fetch_events":"https://pith.science/api/pith-number/UTIV7QROW36P45BMNBNMXGZILM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UTIV7QROW36P45BMNBNMXGZILM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UTIV7QROW36P45BMNBNMXGZILM/action/storage_attestation","attest_author":"https://pith.science/pith/UTIV7QROW36P45BMNBNMXGZILM/action/author_attestation","sign_citation":"https://pith.science/pith/UTIV7QROW36P45BMNBNMXGZILM/action/citation_signature","submit_replication":"https://pith.science/pith/UTIV7QROW36P45BMNBNMXGZILM/action/replication_record"}},"created_at":"2026-07-05T03:33:16.396079+00:00","updated_at":"2026-07-05T03:33:16.396079+00:00"}