{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WAQVUNT3GXU3P3UPJV5KMF3ORR","short_pith_number":"pith:WAQVUNT3","schema_version":"1.0","canonical_sha256":"b0215a367b35e9b7ee8f4d7aa6176e8c575e5925dc589daf44b3e31fb0dcad47","source":{"kind":"arxiv","id":"1902.05698","version":2},"attestation_state":"computed","paper":{"title":"Bi-directional Value Learning for Risk-aware Planning Under Uncertainty: Extended Version","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ali-akbar Agha-mohammadi, Rohan Thakker, Sung-Kyun Kim","submitted_at":"2019-02-15T06:07:57Z","abstract_excerpt":"Decision-making under uncertainty is a crucial ability for autonomous systems. In its most general form, this problem can be formulated as a Partially Observable Markov Decision Process (POMDP). The solution policy of a POMDP can be implicitly encoded as a value function. In partially observable settings, the value function is typically learned via forward simulation of the system evolution. Focusing on accurate and long-range risk assessment, we propose a novel method, where the value function is learned in different phases via a bi-directional search in belief space. A backward value learnin"},"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":"1902.05698","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-02-15T06:07:57Z","cross_cats_sorted":[],"title_canon_sha256":"b9d1187cc60938c87ae80c7c995713f6ccdcee2b3de1d3c891b5070c293a025b","abstract_canon_sha256":"08422bfbe0ec20fe2f7ca42ceb2aeda6913ab5f03bc17480b507f66c19157be0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:14.625640Z","signature_b64":"tVhuSmjSP9vJZ/Ki3vCrB9/M1mhY0XEsU4bNPze+oxhLxh37e99dwjEL0QNwO+pSIa9B5SpF0UJLNyVOQHp4Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0215a367b35e9b7ee8f4d7aa6176e8c575e5925dc589daf44b3e31fb0dcad47","last_reissued_at":"2026-05-17T23:49:14.624897Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:14.624897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bi-directional Value Learning for Risk-aware Planning Under Uncertainty: Extended Version","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ali-akbar Agha-mohammadi, Rohan Thakker, Sung-Kyun Kim","submitted_at":"2019-02-15T06:07:57Z","abstract_excerpt":"Decision-making under uncertainty is a crucial ability for autonomous systems. In its most general form, this problem can be formulated as a Partially Observable Markov Decision Process (POMDP). The solution policy of a POMDP can be implicitly encoded as a value function. In partially observable settings, the value function is typically learned via forward simulation of the system evolution. Focusing on accurate and long-range risk assessment, we propose a novel method, where the value function is learned in different phases via a bi-directional search in belief space. A backward value learnin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.05698","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1902.05698","created_at":"2026-05-17T23:49:14.625007+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.05698v2","created_at":"2026-05-17T23:49:14.625007+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.05698","created_at":"2026-05-17T23:49:14.625007+00:00"},{"alias_kind":"pith_short_12","alias_value":"WAQVUNT3GXU3","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"WAQVUNT3GXU3P3UP","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"WAQVUNT3","created_at":"2026-05-18T12:33:30.264802+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/WAQVUNT3GXU3P3UPJV5KMF3ORR","json":"https://pith.science/pith/WAQVUNT3GXU3P3UPJV5KMF3ORR.json","graph_json":"https://pith.science/api/pith-number/WAQVUNT3GXU3P3UPJV5KMF3ORR/graph.json","events_json":"https://pith.science/api/pith-number/WAQVUNT3GXU3P3UPJV5KMF3ORR/events.json","paper":"https://pith.science/paper/WAQVUNT3"},"agent_actions":{"view_html":"https://pith.science/pith/WAQVUNT3GXU3P3UPJV5KMF3ORR","download_json":"https://pith.science/pith/WAQVUNT3GXU3P3UPJV5KMF3ORR.json","view_paper":"https://pith.science/paper/WAQVUNT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.05698&json=true","fetch_graph":"https://pith.science/api/pith-number/WAQVUNT3GXU3P3UPJV5KMF3ORR/graph.json","fetch_events":"https://pith.science/api/pith-number/WAQVUNT3GXU3P3UPJV5KMF3ORR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WAQVUNT3GXU3P3UPJV5KMF3ORR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WAQVUNT3GXU3P3UPJV5KMF3ORR/action/storage_attestation","attest_author":"https://pith.science/pith/WAQVUNT3GXU3P3UPJV5KMF3ORR/action/author_attestation","sign_citation":"https://pith.science/pith/WAQVUNT3GXU3P3UPJV5KMF3ORR/action/citation_signature","submit_replication":"https://pith.science/pith/WAQVUNT3GXU3P3UPJV5KMF3ORR/action/replication_record"}},"created_at":"2026-05-17T23:49:14.625007+00:00","updated_at":"2026-05-17T23:49:14.625007+00:00"}