{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CP2X56JCZS5Q3LSDJPWPNDCNK3","short_pith_number":"pith:CP2X56JC","schema_version":"1.0","canonical_sha256":"13f57ef922ccbb0dae434becf68c4d56cc97208c86478a3f4fdc715d1834ad3c","source":{"kind":"arxiv","id":"2306.11488","version":3},"attestation_state":"computed","paper":{"title":"Informed POMDP: Leveraging Additional Information in Model-Based RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adrien Bolland, Damien Ernst, Gaspard Lambrechts","submitted_at":"2023-06-20T12:20:23Z","abstract_excerpt":"In this work, we generalize the problem of learning through interaction in a POMDP by accounting for eventual additional information available at training time. First, we introduce the informed POMDP, a new learning paradigm offering a clear distinction between the information at training and the observation at execution. Next, we propose an objective that leverages this information for learning a sufficient statistic of the history for the optimal control. We then adapt this informed objective to learn a world model able to sample latent trajectories. Finally, we empirically show a learning s"},"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":"2306.11488","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-20T12:20:23Z","cross_cats_sorted":[],"title_canon_sha256":"aed0dab0ad15d9777b6e8f35306df7f964e065526ac80709f0b740e1ecc43a37","abstract_canon_sha256":"8703849628a8d4dab3cee0dd1649e006714f272c48bfb283dc320363d00f86ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:47.528226Z","signature_b64":"a5TYS/ZrGIuBDoSpOc+t2ydKfPJ5fie1W+AkzpdKjnB+cJEZHztkuT37kdgZ0cSm94wqBIH/SFFdknAxIDRPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13f57ef922ccbb0dae434becf68c4d56cc97208c86478a3f4fdc715d1834ad3c","last_reissued_at":"2026-07-05T11:16:47.527708Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:47.527708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Informed POMDP: Leveraging Additional Information in Model-Based RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adrien Bolland, Damien Ernst, Gaspard Lambrechts","submitted_at":"2023-06-20T12:20:23Z","abstract_excerpt":"In this work, we generalize the problem of learning through interaction in a POMDP by accounting for eventual additional information available at training time. First, we introduce the informed POMDP, a new learning paradigm offering a clear distinction between the information at training and the observation at execution. Next, we propose an objective that leverages this information for learning a sufficient statistic of the history for the optimal control. We then adapt this informed objective to learn a world model able to sample latent trajectories. Finally, we empirically show a learning s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11488","kind":"arxiv","version":3},"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/2306.11488/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":"2306.11488","created_at":"2026-07-05T11:16:47.527770+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.11488v3","created_at":"2026-07-05T11:16:47.527770+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11488","created_at":"2026-07-05T11:16:47.527770+00:00"},{"alias_kind":"pith_short_12","alias_value":"CP2X56JCZS5Q","created_at":"2026-07-05T11:16:47.527770+00:00"},{"alias_kind":"pith_short_16","alias_value":"CP2X56JCZS5Q3LSD","created_at":"2026-07-05T11:16:47.527770+00:00"},{"alias_kind":"pith_short_8","alias_value":"CP2X56JC","created_at":"2026-07-05T11:16:47.527770+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/CP2X56JCZS5Q3LSDJPWPNDCNK3","json":"https://pith.science/pith/CP2X56JCZS5Q3LSDJPWPNDCNK3.json","graph_json":"https://pith.science/api/pith-number/CP2X56JCZS5Q3LSDJPWPNDCNK3/graph.json","events_json":"https://pith.science/api/pith-number/CP2X56JCZS5Q3LSDJPWPNDCNK3/events.json","paper":"https://pith.science/paper/CP2X56JC"},"agent_actions":{"view_html":"https://pith.science/pith/CP2X56JCZS5Q3LSDJPWPNDCNK3","download_json":"https://pith.science/pith/CP2X56JCZS5Q3LSDJPWPNDCNK3.json","view_paper":"https://pith.science/paper/CP2X56JC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.11488&json=true","fetch_graph":"https://pith.science/api/pith-number/CP2X56JCZS5Q3LSDJPWPNDCNK3/graph.json","fetch_events":"https://pith.science/api/pith-number/CP2X56JCZS5Q3LSDJPWPNDCNK3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CP2X56JCZS5Q3LSDJPWPNDCNK3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CP2X56JCZS5Q3LSDJPWPNDCNK3/action/storage_attestation","attest_author":"https://pith.science/pith/CP2X56JCZS5Q3LSDJPWPNDCNK3/action/author_attestation","sign_citation":"https://pith.science/pith/CP2X56JCZS5Q3LSDJPWPNDCNK3/action/citation_signature","submit_replication":"https://pith.science/pith/CP2X56JCZS5Q3LSDJPWPNDCNK3/action/replication_record"}},"created_at":"2026-07-05T11:16:47.527770+00:00","updated_at":"2026-07-05T11:16:47.527770+00:00"}