{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:BJNPQEK3RPZJ3SPQPJ32YRUCAC","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":"c523f44736736a50b33771c7d9c16a2b6538c94b53c0a0d0390bb27c5a36aaca","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-06-11T07:06:06Z","title_canon_sha256":"9e725fb691c8ffa7a0f5f6010eb83e9653484aeaf07631f7cc463ce1bcfba5fe"},"schema_version":"1.0","source":{"id":"1906.05130","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05130","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05130v1","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05130","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"pith_short_12","alias_value":"BJNPQEK3RPZJ","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"BJNPQEK3RPZJ3SPQ","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"BJNPQEK3","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:7c993b6beac58d9b405ee055ac5b196a4d0ecedf00906207ecd2cc61e6969355","target":"graph","created_at":"2026-05-17T23:43:29Z","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":"How an agent can act optimally in stochastic, partially observable domains is a challenge problem, the standard approach to address this issue is to learn the domain model firstly and then based on the learned model to find the (near) optimal policy. However, offline learning the model often needs to store the entire training data and cannot utilize the data generated in the planning phase. Furthermore, current research usually assumes the learned model is accurate or presupposes knowledge of the nature of the unobservable part of the world. In this paper, for systems with discrete settings, w","authors_text":"Jianyang Zheng, Yunlong Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-06-11T07:06:06Z","title":"Online Learning and Planning in Partially Observable Domains without Prior Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05130","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":"sha256:99bae8e253d7a0c9a876141f70e55390261d5309222242fbf8473f0d6b5200aa","target":"record","created_at":"2026-05-17T23:43:29Z","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":"c523f44736736a50b33771c7d9c16a2b6538c94b53c0a0d0390bb27c5a36aaca","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-06-11T07:06:06Z","title_canon_sha256":"9e725fb691c8ffa7a0f5f6010eb83e9653484aeaf07631f7cc463ce1bcfba5fe"},"schema_version":"1.0","source":{"id":"1906.05130","kind":"arxiv","version":1}},"canonical_sha256":"0a5af8115b8bf29dc9f07a77ac468200b7d2b8c2820a32bfc967b091006e0bb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a5af8115b8bf29dc9f07a77ac468200b7d2b8c2820a32bfc967b091006e0bb2","first_computed_at":"2026-05-17T23:43:29.372990Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:29.372990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ynZNajR9u01IEhBLYCb2SHcyQ0sgtm58j8huY4R6VhphknzzfS+Npe7uo4mxFSFWb9+nhOxcg5p3PZpEVIxXAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:29.373719Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.05130","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99bae8e253d7a0c9a876141f70e55390261d5309222242fbf8473f0d6b5200aa","sha256:7c993b6beac58d9b405ee055ac5b196a4d0ecedf00906207ecd2cc61e6969355"],"state_sha256":"bda5da3806abf05bcbde19b8b40ee0781dc0b165103f157d44cfcf78318db4f7"}