{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ORAXQBNR53ULPVHW3FP5JOKU46","short_pith_number":"pith:ORAXQBNR","schema_version":"1.0","canonical_sha256":"74417805b1eee8b7d4f6d95fd4b954e79fedd6f15a54478f55348ae2171411b2","source":{"kind":"arxiv","id":"1905.05731","version":1},"attestation_state":"computed","paper":{"title":"Successor Options: An Option Discovery Framework for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Balaraman Ravindran, Manan Tomar, Rahul Ramesh","submitted_at":"2019-05-14T17:24:11Z","abstract_excerpt":"The options framework in reinforcement learning models the notion of a skill or a temporally extended sequence of actions. The discovery of a reusable set of skills has typically entailed building options, that navigate to bottleneck states. This work adopts a complementary approach, where we attempt to discover options that navigate to landmark states. These states are prototypical representatives of well-connected regions and can hence access the associated region with relative ease. In this work, we propose Successor Options, which leverages Successor Representations to build a model of the"},"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":"1905.05731","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-14T17:24:11Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"8abffa43dca22edb8a3ea9a434643c616f95d3cda667565dd5e62dc76a39ed0d","abstract_canon_sha256":"e2b083615cbbf9bfec2967e46bec2c5106cd5574a81a29a30414683e03d0f44c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:13.711782Z","signature_b64":"tKfu0IeQkytJ/UReHlsWjoVeg3g0DMl8ZGHpk/KjDc9lV+/NUCOd8Sou71d911B/n54jIDKAjIazqX3dLdmIAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74417805b1eee8b7d4f6d95fd4b954e79fedd6f15a54478f55348ae2171411b2","last_reissued_at":"2026-05-17T23:46:13.711345Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:13.711345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Successor Options: An Option Discovery Framework for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Balaraman Ravindran, Manan Tomar, Rahul Ramesh","submitted_at":"2019-05-14T17:24:11Z","abstract_excerpt":"The options framework in reinforcement learning models the notion of a skill or a temporally extended sequence of actions. The discovery of a reusable set of skills has typically entailed building options, that navigate to bottleneck states. This work adopts a complementary approach, where we attempt to discover options that navigate to landmark states. These states are prototypical representatives of well-connected regions and can hence access the associated region with relative ease. In this work, we propose Successor Options, which leverages Successor Representations to build a model of the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05731","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":""},"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":"1905.05731","created_at":"2026-05-17T23:46:13.711413+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.05731v1","created_at":"2026-05-17T23:46:13.711413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05731","created_at":"2026-05-17T23:46:13.711413+00:00"},{"alias_kind":"pith_short_12","alias_value":"ORAXQBNR53UL","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"ORAXQBNR53ULPVHW","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"ORAXQBNR","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.13207","citing_title":"Switching Successor Measures for Hierarchical Zero-shot Reinforcement Learning","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ORAXQBNR53ULPVHW3FP5JOKU46","json":"https://pith.science/pith/ORAXQBNR53ULPVHW3FP5JOKU46.json","graph_json":"https://pith.science/api/pith-number/ORAXQBNR53ULPVHW3FP5JOKU46/graph.json","events_json":"https://pith.science/api/pith-number/ORAXQBNR53ULPVHW3FP5JOKU46/events.json","paper":"https://pith.science/paper/ORAXQBNR"},"agent_actions":{"view_html":"https://pith.science/pith/ORAXQBNR53ULPVHW3FP5JOKU46","download_json":"https://pith.science/pith/ORAXQBNR53ULPVHW3FP5JOKU46.json","view_paper":"https://pith.science/paper/ORAXQBNR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.05731&json=true","fetch_graph":"https://pith.science/api/pith-number/ORAXQBNR53ULPVHW3FP5JOKU46/graph.json","fetch_events":"https://pith.science/api/pith-number/ORAXQBNR53ULPVHW3FP5JOKU46/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ORAXQBNR53ULPVHW3FP5JOKU46/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ORAXQBNR53ULPVHW3FP5JOKU46/action/storage_attestation","attest_author":"https://pith.science/pith/ORAXQBNR53ULPVHW3FP5JOKU46/action/author_attestation","sign_citation":"https://pith.science/pith/ORAXQBNR53ULPVHW3FP5JOKU46/action/citation_signature","submit_replication":"https://pith.science/pith/ORAXQBNR53ULPVHW3FP5JOKU46/action/replication_record"}},"created_at":"2026-05-17T23:46:13.711413+00:00","updated_at":"2026-05-17T23:46:13.711413+00:00"}