{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BPU2U4LECEOF7O2WZF5X2G3IRQ","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":"fa75e1ddfe54c258e882bfc02c9d8f599f3ebe92a1afc25b0e9acc95a3e9f2da","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-30T12:10:07Z","title_canon_sha256":"509bfe057197af1f8cc3c07908fdadd3db9ec7fabc6e829608ecb7454a335dc4"},"schema_version":"1.0","source":{"id":"2006.16712","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.16712","created_at":"2026-07-05T04:10:20Z"},{"alias_kind":"arxiv_version","alias_value":"2006.16712v4","created_at":"2026-07-05T04:10:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.16712","created_at":"2026-07-05T04:10:20Z"},{"alias_kind":"pith_short_12","alias_value":"BPU2U4LECEOF","created_at":"2026-07-05T04:10:20Z"},{"alias_kind":"pith_short_16","alias_value":"BPU2U4LECEOF7O2W","created_at":"2026-07-05T04:10:20Z"},{"alias_kind":"pith_short_8","alias_value":"BPU2U4LE","created_at":"2026-07-05T04:10:20Z"}],"graph_snapshots":[{"event_id":"sha256:ac5636b9c0032f4f96e2410e50bf6051e31808973f45d4cd5f4dc87b021c2509","target":"graph","created_at":"2026-07-05T04:10:20Z","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/2006.16712/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sequential decision making, commonly formalized as Markov Decision Process (MDP) optimization, is a important challenge in artificial intelligence. Two key approaches to this problem are reinforcement learning (RL) and planning. This paper presents a survey of the integration of both fields, better known as model-based reinforcement learning. Model-based RL has two main steps. First, we systematically cover approaches to dynamics model learning, including challenges like dealing with stochasticity, uncertainty, partial observability, and temporal abstraction. Second, we present a systematic ca","authors_text":"Aske Plaat, Catholijn M. Jonker, Joost Broekens, Thomas M. Moerland","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-30T12:10:07Z","title":"Model-based Reinforcement Learning: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.16712","kind":"arxiv","version":4},"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":"sha256:6fea4a9791956b9413a28ca1c140a0ef67fcda1349b52ecb02d863c3610d1792","target":"record","created_at":"2026-07-05T04:10:20Z","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":"fa75e1ddfe54c258e882bfc02c9d8f599f3ebe92a1afc25b0e9acc95a3e9f2da","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-30T12:10:07Z","title_canon_sha256":"509bfe057197af1f8cc3c07908fdadd3db9ec7fabc6e829608ecb7454a335dc4"},"schema_version":"1.0","source":{"id":"2006.16712","kind":"arxiv","version":4}},"canonical_sha256":"0be9aa7164111c5fbb56c97b7d1b688c0355faaebcd2c28752dbe49757e2ef26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0be9aa7164111c5fbb56c97b7d1b688c0355faaebcd2c28752dbe49757e2ef26","first_computed_at":"2026-07-05T04:10:20.855953Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:10:20.855953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cTxg9MxVbS/zDcbO1BpR8y/dAobM/ePdOpZxdEnDqSLBHq9Kof8/mMW13DpQbOTNCyrYa6rrFs+LRJjS8DkgAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:10:20.856407Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.16712","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6fea4a9791956b9413a28ca1c140a0ef67fcda1349b52ecb02d863c3610d1792","sha256:ac5636b9c0032f4f96e2410e50bf6051e31808973f45d4cd5f4dc87b021c2509"],"state_sha256":"8f370dc5614b086097beb5a048d95e22014c4292e6433a251e37912a1c08f679"}