{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:G7A27RAK2XX7GCAWDCTTLEKA3N","short_pith_number":"pith:G7A27RAK","canonical_record":{"source":{"id":"1708.06551","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-08-22T09:51:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7ffc0c2d8bbbf08757bde07433211fc4bd53be97da5a478ed7930d52cb9bb04b","abstract_canon_sha256":"8a61d9dfa3ba7471b8ea53686f6bae5074d7db6bb0eeac71fe5eca475f1c145a"},"schema_version":"1.0"},"canonical_sha256":"37c1afc40ad5eff3081618a7359140db7cc08341ae63c034dd4d5d4ee476df0a","source":{"kind":"arxiv","id":"1708.06551","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.06551","created_at":"2026-05-18T00:35:30Z"},{"alias_kind":"arxiv_version","alias_value":"1708.06551v2","created_at":"2026-05-18T00:35:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.06551","created_at":"2026-05-18T00:35:30Z"},{"alias_kind":"pith_short_12","alias_value":"G7A27RAK2XX7","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"G7A27RAK2XX7GCAW","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"G7A27RAK","created_at":"2026-05-18T12:31:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:G7A27RAK2XX7GCAWDCTTLEKA3N","target":"record","payload":{"canonical_record":{"source":{"id":"1708.06551","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-08-22T09:51:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7ffc0c2d8bbbf08757bde07433211fc4bd53be97da5a478ed7930d52cb9bb04b","abstract_canon_sha256":"8a61d9dfa3ba7471b8ea53686f6bae5074d7db6bb0eeac71fe5eca475f1c145a"},"schema_version":"1.0"},"canonical_sha256":"37c1afc40ad5eff3081618a7359140db7cc08341ae63c034dd4d5d4ee476df0a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:30.524158Z","signature_b64":"dZeY4RKqNFO5hvYhvNiR/HXkBJCK44k5qXmP6TcfvGR7MnBdCclEhfhDubImpnaFBNDtUvFNfUkhWopsjpP5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37c1afc40ad5eff3081618a7359140db7cc08341ae63c034dd4d5d4ee476df0a","last_reissued_at":"2026-05-18T00:35:30.523638Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:30.523638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.06551","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:35:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dbnQWLdDH0ov8jmvXo30dxHgppVy2RoC/Xgn9u6bN6QJqICtNSkGtIQmH+2YOaTxDmY4Zpo83b6ZK7718Nf9DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T23:18:59.517348Z"},"content_sha256":"0997c893004dccfbca855b7e166e6f0a40181a36d4b0bd6884a3f8fdc374795b","schema_version":"1.0","event_id":"sha256:0997c893004dccfbca855b7e166e6f0a40181a36d4b0bd6884a3f8fdc374795b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:G7A27RAK2XX7GCAWDCTTLEKA3N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning in POMDPs with Memoryless Options and Option-Observation Initiation Sets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Anna Harutyunyan, Ann Now\\'e, Denis Steckelmacher, Diederik M. Roijers, H\\'el\\`ene Plisnier, Peter Vrancx","submitted_at":"2017-08-22T09:51:18Z","abstract_excerpt":"Many real-world reinforcement learning problems have a hierarchical nature, and often exhibit some degree of partial observability. While hierarchy and partial observability are usually tackled separately (for instance by combining recurrent neural networks and options), we show that addressing both problems simultaneously is simpler and more efficient in many cases. More specifically, we make the initiation set of options conditional on the previously-executed option, and show that options with such Option-Observation Initiation Sets (OOIs) are at least as expressive as Finite State Controlle"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.06551","kind":"arxiv","version":2},"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":"2026-05-18T00:35:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cnDKv4HnxS9dYi7ziA1ejVRWVWM9ymr/sV/T/uDf0Tg3fm0cp+6S7CnoFfGNfZaPbwPe8n4KZuP6bCGKPbVxAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T23:18:59.517975Z"},"content_sha256":"eab95ad6a7cba01a9aabd386eb4146223f921b3c307a53cd6865e3d61f3db6e8","schema_version":"1.0","event_id":"sha256:eab95ad6a7cba01a9aabd386eb4146223f921b3c307a53cd6865e3d61f3db6e8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G7A27RAK2XX7GCAWDCTTLEKA3N/bundle.json","state_url":"https://pith.science/pith/G7A27RAK2XX7GCAWDCTTLEKA3N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G7A27RAK2XX7GCAWDCTTLEKA3N/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":"2026-05-27T23:18:59Z","links":{"resolver":"https://pith.science/pith/G7A27RAK2XX7GCAWDCTTLEKA3N","bundle":"https://pith.science/pith/G7A27RAK2XX7GCAWDCTTLEKA3N/bundle.json","state":"https://pith.science/pith/G7A27RAK2XX7GCAWDCTTLEKA3N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G7A27RAK2XX7GCAWDCTTLEKA3N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:G7A27RAK2XX7GCAWDCTTLEKA3N","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":"8a61d9dfa3ba7471b8ea53686f6bae5074d7db6bb0eeac71fe5eca475f1c145a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-08-22T09:51:18Z","title_canon_sha256":"7ffc0c2d8bbbf08757bde07433211fc4bd53be97da5a478ed7930d52cb9bb04b"},"schema_version":"1.0","source":{"id":"1708.06551","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.06551","created_at":"2026-05-18T00:35:30Z"},{"alias_kind":"arxiv_version","alias_value":"1708.06551v2","created_at":"2026-05-18T00:35:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.06551","created_at":"2026-05-18T00:35:30Z"},{"alias_kind":"pith_short_12","alias_value":"G7A27RAK2XX7","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"G7A27RAK2XX7GCAW","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"G7A27RAK","created_at":"2026-05-18T12:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:eab95ad6a7cba01a9aabd386eb4146223f921b3c307a53cd6865e3d61f3db6e8","target":"graph","created_at":"2026-05-18T00:35:30Z","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":"Many real-world reinforcement learning problems have a hierarchical nature, and often exhibit some degree of partial observability. While hierarchy and partial observability are usually tackled separately (for instance by combining recurrent neural networks and options), we show that addressing both problems simultaneously is simpler and more efficient in many cases. More specifically, we make the initiation set of options conditional on the previously-executed option, and show that options with such Option-Observation Initiation Sets (OOIs) are at least as expressive as Finite State Controlle","authors_text":"Anna Harutyunyan, Ann Now\\'e, Denis Steckelmacher, Diederik M. Roijers, H\\'el\\`ene Plisnier, Peter Vrancx","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-08-22T09:51:18Z","title":"Reinforcement Learning in POMDPs with Memoryless Options and Option-Observation Initiation Sets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.06551","kind":"arxiv","version":2},"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":"sha256:0997c893004dccfbca855b7e166e6f0a40181a36d4b0bd6884a3f8fdc374795b","target":"record","created_at":"2026-05-18T00:35:30Z","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":"8a61d9dfa3ba7471b8ea53686f6bae5074d7db6bb0eeac71fe5eca475f1c145a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-08-22T09:51:18Z","title_canon_sha256":"7ffc0c2d8bbbf08757bde07433211fc4bd53be97da5a478ed7930d52cb9bb04b"},"schema_version":"1.0","source":{"id":"1708.06551","kind":"arxiv","version":2}},"canonical_sha256":"37c1afc40ad5eff3081618a7359140db7cc08341ae63c034dd4d5d4ee476df0a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37c1afc40ad5eff3081618a7359140db7cc08341ae63c034dd4d5d4ee476df0a","first_computed_at":"2026-05-18T00:35:30.523638Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:35:30.523638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dZeY4RKqNFO5hvYhvNiR/HXkBJCK44k5qXmP6TcfvGR7MnBdCclEhfhDubImpnaFBNDtUvFNfUkhWopsjpP5DQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:35:30.524158Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.06551","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0997c893004dccfbca855b7e166e6f0a40181a36d4b0bd6884a3f8fdc374795b","sha256:eab95ad6a7cba01a9aabd386eb4146223f921b3c307a53cd6865e3d61f3db6e8"],"state_sha256":"1a7a974db5009bc13149f43c41855ae2a6d8378fa13b954ee8393c70decf86fe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"In+FhF1N/MvEFyCE+2u7EQaZwgVgCfz9Q1WfiOqerD4t39IaKYbwqx5tBkcjFtGbck1fDTWBmNJdCT6Ju+9xAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T23:18:59.521276Z","bundle_sha256":"8981ca5646696c822e95d2b5b5603226b16b0316340720c0ffd7d1ee5e46cbde"}}