{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3YSLD3Y2ZM3FKTIDUO3XA2XHVG","short_pith_number":"pith:3YSLD3Y2","schema_version":"1.0","canonical_sha256":"de24b1ef1acb36554d03a3b7706ae7a98fe0152e8039ded1de5bb568da173149","source":{"kind":"arxiv","id":"2402.09388","version":1},"attestation_state":"computed","paper":{"title":"Entropy-regularized Point-based Value Iteration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Esen Yel, Harrison Delecki, Kyle Wray, Marcell Vazquez-Chanlatte, Mykel J. Kochenderfer, Stefan Witwicki, Tomer Arnon","submitted_at":"2024-02-14T18:37:47Z","abstract_excerpt":"Model-based planners for partially observable problems must accommodate both model uncertainty during planning and goal uncertainty during objective inference. However, model-based planners may be brittle under these types of uncertainty because they rely on an exact model and tend to commit to a single optimal behavior. Inspired by results in the model-free setting, we propose an entropy-regularized model-based planner for partially observable problems. Entropy regularization promotes policy robustness for planning and objective inference by encouraging policies to be no more committed to a 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":"2402.09388","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-14T18:37:47Z","cross_cats_sorted":[],"title_canon_sha256":"41bce6fcb462055c4700868cf8ee4cfc3016d6969d4f5152e257e778de936457","abstract_canon_sha256":"34db73eec8395aeb069ae6588b78fddedc3a7e1f0463b0b9a414ccb18e6c3900"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:13.163251Z","signature_b64":"PdXgXDy0pJ5etau/M2UpWyl/n0MPrGqNjVxt6KG3w51rc1C5vuouWCPEg0SPEABf4zolegjLBOY1wK5nouxqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de24b1ef1acb36554d03a3b7706ae7a98fe0152e8039ded1de5bb568da173149","last_reissued_at":"2026-07-05T07:45:13.162826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:13.162826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Entropy-regularized Point-based Value Iteration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Esen Yel, Harrison Delecki, Kyle Wray, Marcell Vazquez-Chanlatte, Mykel J. Kochenderfer, Stefan Witwicki, Tomer Arnon","submitted_at":"2024-02-14T18:37:47Z","abstract_excerpt":"Model-based planners for partially observable problems must accommodate both model uncertainty during planning and goal uncertainty during objective inference. However, model-based planners may be brittle under these types of uncertainty because they rely on an exact model and tend to commit to a single optimal behavior. Inspired by results in the model-free setting, we propose an entropy-regularized model-based planner for partially observable problems. Entropy regularization promotes policy robustness for planning and objective inference by encouraging policies to be no more committed to a s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09388","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.09388/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":"2402.09388","created_at":"2026-07-05T07:45:13.162882+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.09388v1","created_at":"2026-07-05T07:45:13.162882+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09388","created_at":"2026-07-05T07:45:13.162882+00:00"},{"alias_kind":"pith_short_12","alias_value":"3YSLD3Y2ZM3F","created_at":"2026-07-05T07:45:13.162882+00:00"},{"alias_kind":"pith_short_16","alias_value":"3YSLD3Y2ZM3FKTID","created_at":"2026-07-05T07:45:13.162882+00:00"},{"alias_kind":"pith_short_8","alias_value":"3YSLD3Y2","created_at":"2026-07-05T07:45:13.162882+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04355","citing_title":"Think Fast and Far: Long-Horizon Online POMDP Planning via Rapid State Sampling","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3YSLD3Y2ZM3FKTIDUO3XA2XHVG","json":"https://pith.science/pith/3YSLD3Y2ZM3FKTIDUO3XA2XHVG.json","graph_json":"https://pith.science/api/pith-number/3YSLD3Y2ZM3FKTIDUO3XA2XHVG/graph.json","events_json":"https://pith.science/api/pith-number/3YSLD3Y2ZM3FKTIDUO3XA2XHVG/events.json","paper":"https://pith.science/paper/3YSLD3Y2"},"agent_actions":{"view_html":"https://pith.science/pith/3YSLD3Y2ZM3FKTIDUO3XA2XHVG","download_json":"https://pith.science/pith/3YSLD3Y2ZM3FKTIDUO3XA2XHVG.json","view_paper":"https://pith.science/paper/3YSLD3Y2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.09388&json=true","fetch_graph":"https://pith.science/api/pith-number/3YSLD3Y2ZM3FKTIDUO3XA2XHVG/graph.json","fetch_events":"https://pith.science/api/pith-number/3YSLD3Y2ZM3FKTIDUO3XA2XHVG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3YSLD3Y2ZM3FKTIDUO3XA2XHVG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3YSLD3Y2ZM3FKTIDUO3XA2XHVG/action/storage_attestation","attest_author":"https://pith.science/pith/3YSLD3Y2ZM3FKTIDUO3XA2XHVG/action/author_attestation","sign_citation":"https://pith.science/pith/3YSLD3Y2ZM3FKTIDUO3XA2XHVG/action/citation_signature","submit_replication":"https://pith.science/pith/3YSLD3Y2ZM3FKTIDUO3XA2XHVG/action/replication_record"}},"created_at":"2026-07-05T07:45:13.162882+00:00","updated_at":"2026-07-05T07:45:13.162882+00:00"}