{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BPU2U4LECEOF7O2WZF5X2G3IRQ","short_pith_number":"pith:BPU2U4LE","schema_version":"1.0","canonical_sha256":"0be9aa7164111c5fbb56c97b7d1b688c0355faaebcd2c28752dbe49757e2ef26","source":{"kind":"arxiv","id":"2006.16712","version":4},"attestation_state":"computed","paper":{"title":"Model-based Reinforcement Learning: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aske Plaat, Catholijn M. Jonker, Joost Broekens, Thomas M. Moerland","submitted_at":"2020-06-30T12:10:07Z","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"},"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":"2006.16712","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-30T12:10:07Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"509bfe057197af1f8cc3c07908fdadd3db9ec7fabc6e829608ecb7454a335dc4","abstract_canon_sha256":"fa75e1ddfe54c258e882bfc02c9d8f599f3ebe92a1afc25b0e9acc95a3e9f2da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:20.856407Z","signature_b64":"cTxg9MxVbS/zDcbO1BpR8y/dAobM/ePdOpZxdEnDqSLBHq9Kof8/mMW13DpQbOTNCyrYa6rrFs+LRJjS8DkgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0be9aa7164111c5fbb56c97b7d1b688c0355faaebcd2c28752dbe49757e2ef26","last_reissued_at":"2026-07-05T04:10:20.855953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:20.855953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-based Reinforcement Learning: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aske Plaat, Catholijn M. Jonker, Joost Broekens, Thomas M. Moerland","submitted_at":"2020-06-30T12:10:07Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.16712","kind":"arxiv","version":4},"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/2006.16712/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":"2006.16712","created_at":"2026-07-05T04:10:20.856012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.16712v4","created_at":"2026-07-05T04:10:20.856012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.16712","created_at":"2026-07-05T04:10:20.856012+00:00"},{"alias_kind":"pith_short_12","alias_value":"BPU2U4LECEOF","created_at":"2026-07-05T04:10:20.856012+00:00"},{"alias_kind":"pith_short_16","alias_value":"BPU2U4LECEOF7O2W","created_at":"2026-07-05T04:10:20.856012+00:00"},{"alias_kind":"pith_short_8","alias_value":"BPU2U4LE","created_at":"2026-07-05T04:10:20.856012+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06824","citing_title":"CaLiSym: Learning Symplectic Dynamics of Real-World Systems through Structured Canonical Lifts","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24991","citing_title":"Solving Markov Decision Processes with Future Information via MPC","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19328","citing_title":"UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14811","citing_title":"Learning Ad Hoc Network Dynamics via Graph-Structured World Models","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BPU2U4LECEOF7O2WZF5X2G3IRQ","json":"https://pith.science/pith/BPU2U4LECEOF7O2WZF5X2G3IRQ.json","graph_json":"https://pith.science/api/pith-number/BPU2U4LECEOF7O2WZF5X2G3IRQ/graph.json","events_json":"https://pith.science/api/pith-number/BPU2U4LECEOF7O2WZF5X2G3IRQ/events.json","paper":"https://pith.science/paper/BPU2U4LE"},"agent_actions":{"view_html":"https://pith.science/pith/BPU2U4LECEOF7O2WZF5X2G3IRQ","download_json":"https://pith.science/pith/BPU2U4LECEOF7O2WZF5X2G3IRQ.json","view_paper":"https://pith.science/paper/BPU2U4LE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.16712&json=true","fetch_graph":"https://pith.science/api/pith-number/BPU2U4LECEOF7O2WZF5X2G3IRQ/graph.json","fetch_events":"https://pith.science/api/pith-number/BPU2U4LECEOF7O2WZF5X2G3IRQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BPU2U4LECEOF7O2WZF5X2G3IRQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BPU2U4LECEOF7O2WZF5X2G3IRQ/action/storage_attestation","attest_author":"https://pith.science/pith/BPU2U4LECEOF7O2WZF5X2G3IRQ/action/author_attestation","sign_citation":"https://pith.science/pith/BPU2U4LECEOF7O2WZF5X2G3IRQ/action/citation_signature","submit_replication":"https://pith.science/pith/BPU2U4LECEOF7O2WZF5X2G3IRQ/action/replication_record"}},"created_at":"2026-07-05T04:10:20.856012+00:00","updated_at":"2026-07-05T04:10:20.856012+00:00"}