{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ORAXQBNR53ULPVHW3FP5JOKU46","short_pith_number":"pith:ORAXQBNR","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"},"canonical_sha256":"74417805b1eee8b7d4f6d95fd4b954e79fedd6f15a54478f55348ae2171411b2","source":{"kind":"arxiv","id":"1905.05731","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.05731","created_at":"2026-05-17T23:46:13Z"},{"alias_kind":"arxiv_version","alias_value":"1905.05731v1","created_at":"2026-05-17T23:46:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05731","created_at":"2026-05-17T23:46:13Z"},{"alias_kind":"pith_short_12","alias_value":"ORAXQBNR53UL","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"ORAXQBNR53ULPVHW","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"ORAXQBNR","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ORAXQBNR53ULPVHW3FP5JOKU46","target":"record","payload":{"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"},"canonical_sha256":"74417805b1eee8b7d4f6d95fd4b954e79fedd6f15a54478f55348ae2171411b2","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"},"source_kind":"arxiv","source_id":"1905.05731","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:46:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZVdNN+DJ71vIsYZG2ODXQuF7gsINB33SULCmvJagcXjssfqkkFN4UoOefMbLpYp+YVbJipc8mUMwjWAmDI8hAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:00:50.340734Z"},"content_sha256":"02fd86c173d6d1b30ef159ea2f4a8e08036964e910528292e4c4f71c22bffd48","schema_version":"1.0","event_id":"sha256:02fd86c173d6d1b30ef159ea2f4a8e08036964e910528292e4c4f71c22bffd48"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ORAXQBNR53ULPVHW3FP5JOKU46","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:46:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bmly/Zk8DflHznP2cfVN3eyK5r3UhJHeySw06ptyYLQtIX4tB0qTpEvnxFPHqAvIsDYQBL8Wpc7XsmvJHCC3Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:00:50.341374Z"},"content_sha256":"f8432de69a34a6e1ef7a4cbb6fb67e4dd617dc53fafe50d8716ba7ca13665c7e","schema_version":"1.0","event_id":"sha256:f8432de69a34a6e1ef7a4cbb6fb67e4dd617dc53fafe50d8716ba7ca13665c7e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ORAXQBNR53ULPVHW3FP5JOKU46/bundle.json","state_url":"https://pith.science/pith/ORAXQBNR53ULPVHW3FP5JOKU46/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ORAXQBNR53ULPVHW3FP5JOKU46/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T17:00:50Z","links":{"resolver":"https://pith.science/pith/ORAXQBNR53ULPVHW3FP5JOKU46","bundle":"https://pith.science/pith/ORAXQBNR53ULPVHW3FP5JOKU46/bundle.json","state":"https://pith.science/pith/ORAXQBNR53ULPVHW3FP5JOKU46/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ORAXQBNR53ULPVHW3FP5JOKU46/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ORAXQBNR53ULPVHW3FP5JOKU46","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":"e2b083615cbbf9bfec2967e46bec2c5106cd5574a81a29a30414683e03d0f44c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-14T17:24:11Z","title_canon_sha256":"8abffa43dca22edb8a3ea9a434643c616f95d3cda667565dd5e62dc76a39ed0d"},"schema_version":"1.0","source":{"id":"1905.05731","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.05731","created_at":"2026-05-17T23:46:13Z"},{"alias_kind":"arxiv_version","alias_value":"1905.05731v1","created_at":"2026-05-17T23:46:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05731","created_at":"2026-05-17T23:46:13Z"},{"alias_kind":"pith_short_12","alias_value":"ORAXQBNR53UL","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"ORAXQBNR53ULPVHW","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"ORAXQBNR","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:f8432de69a34a6e1ef7a4cbb6fb67e4dd617dc53fafe50d8716ba7ca13665c7e","target":"graph","created_at":"2026-05-17T23:46:13Z","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"},"paper":{"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","authors_text":"Balaraman Ravindran, Manan Tomar, Rahul Ramesh","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-14T17:24:11Z","title":"Successor Options: An Option Discovery Framework for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05731","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":"sha256:02fd86c173d6d1b30ef159ea2f4a8e08036964e910528292e4c4f71c22bffd48","target":"record","created_at":"2026-05-17T23:46:13Z","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":"e2b083615cbbf9bfec2967e46bec2c5106cd5574a81a29a30414683e03d0f44c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-14T17:24:11Z","title_canon_sha256":"8abffa43dca22edb8a3ea9a434643c616f95d3cda667565dd5e62dc76a39ed0d"},"schema_version":"1.0","source":{"id":"1905.05731","kind":"arxiv","version":1}},"canonical_sha256":"74417805b1eee8b7d4f6d95fd4b954e79fedd6f15a54478f55348ae2171411b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74417805b1eee8b7d4f6d95fd4b954e79fedd6f15a54478f55348ae2171411b2","first_computed_at":"2026-05-17T23:46:13.711345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:13.711345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tKfu0IeQkytJ/UReHlsWjoVeg3g0DMl8ZGHpk/KjDc9lV+/NUCOd8Sou71d911B/n54jIDKAjIazqX3dLdmIAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:13.711782Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.05731","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02fd86c173d6d1b30ef159ea2f4a8e08036964e910528292e4c4f71c22bffd48","sha256:f8432de69a34a6e1ef7a4cbb6fb67e4dd617dc53fafe50d8716ba7ca13665c7e"],"state_sha256":"5b711db44d0dba9d1f95eaa6856f75e544bc0aca44f1b8268a74252395a58d3e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eUr3J8Un5A4Na9u9Jap42abK0VJ0re2kFHGgz5F2feVLQetDanUl5gKtophg/RWkw+dgjwcrYfx9FC0GjfHXBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T17:00:50.345363Z","bundle_sha256":"0cd39b6932d68d0f48125f7cf92f3bc59c5c54b2aaeafb9f7d16eadbc98274d2"}}