{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WFP6AGEK463DLCRPSQTY2PEDGG","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":"032aa7d2617e858bd2a8f9a087b363601ec41a8d98aa8da6ff54d93e83ffa178","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-18T02:10:45Z","title_canon_sha256":"7f31d53c0ac342d46a3d93d7367e6dafc8b60e12db7388eaa1f1804886b4947b"},"schema_version":"1.0","source":{"id":"2308.09733","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.09733","created_at":"2026-07-05T06:42:45Z"},{"alias_kind":"arxiv_version","alias_value":"2308.09733v1","created_at":"2026-07-05T06:42:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.09733","created_at":"2026-07-05T06:42:45Z"},{"alias_kind":"pith_short_12","alias_value":"WFP6AGEK463D","created_at":"2026-07-05T06:42:45Z"},{"alias_kind":"pith_short_16","alias_value":"WFP6AGEK463DLCRP","created_at":"2026-07-05T06:42:45Z"},{"alias_kind":"pith_short_8","alias_value":"WFP6AGEK","created_at":"2026-07-05T06:42:45Z"}],"graph_snapshots":[{"event_id":"sha256:26787d954cedcd9cef71ce6202653811264a9d74122b7b1b25d7778595655b25","target":"graph","created_at":"2026-07-05T06:42:45Z","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/2308.09733/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-objective Markov decision processes are sequential decision-making problems that involve multiple conflicting reward functions that cannot be optimized simultaneously without a compromise. This type of problems cannot be solved by a single optimal policy as in the conventional case. Alternatively, multi-objective reinforcement learning methods evolve a coverage set of optimal policies that can satisfy all possible preferences in solving the problem. However, many of these methods cannot generalize their coverage sets to work in non-stationary environments. In these environments, the para","authors_text":"Jiankun Hu, Kathryn Merrick, Sherif Abdelfattah","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-18T02:10:45Z","title":"Intrinsically Motivated Hierarchical Policy Learning in Multi-objective Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.09733","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":"sha256:364b52627cb09ca7b013acd5ad1872eaa59073b965ed9987d2eb5bdaeb76c9d3","target":"record","created_at":"2026-07-05T06:42:45Z","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":"032aa7d2617e858bd2a8f9a087b363601ec41a8d98aa8da6ff54d93e83ffa178","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-18T02:10:45Z","title_canon_sha256":"7f31d53c0ac342d46a3d93d7367e6dafc8b60e12db7388eaa1f1804886b4947b"},"schema_version":"1.0","source":{"id":"2308.09733","kind":"arxiv","version":1}},"canonical_sha256":"b15fe0188ae7b6358a2f94278d3c8331ba38fa8862fa8380cbac6cf1fe610bed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b15fe0188ae7b6358a2f94278d3c8331ba38fa8862fa8380cbac6cf1fe610bed","first_computed_at":"2026-07-05T06:42:45.954510Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:42:45.954510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BwzcytCTVx+l5tcU84LYY0LPHN0H0KZeDaZM+1+5EAwAwe4gEPXh3vQe/OTNdtU8zDN70I7PTxTq2LPH2Z26Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:42:45.954956Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.09733","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:364b52627cb09ca7b013acd5ad1872eaa59073b965ed9987d2eb5bdaeb76c9d3","sha256:26787d954cedcd9cef71ce6202653811264a9d74122b7b1b25d7778595655b25"],"state_sha256":"88bd1d645ab7689f43879ac1226a1a1968585167eb96445e3d08f2f3fa9ababb"}