{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SFJBFLHSBZSXAJOYDG7NG7APNZ","short_pith_number":"pith:SFJBFLHS","schema_version":"1.0","canonical_sha256":"915212acf20e657025d819bed37c0f6e633a2732272e46c0abce27ddbca64934","source":{"kind":"arxiv","id":"2301.10067","version":1},"attestation_state":"computed","paper":{"title":"Intrinsic Motivation in Model-based Reinforcement Learning: A Brief Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aleksandr I. Panov, Artem Latyshev","submitted_at":"2023-01-24T15:13:02Z","abstract_excerpt":"The reinforcement learning research area contains a wide range of methods for solving the problems of intelligent agent control. Despite the progress that has been made, the task of creating a highly autonomous agent is still a significant challenge. One potential solution to this problem is intrinsic motivation, a concept derived from developmental psychology. This review considers the existing methods for determining intrinsic motivation based on the world model obtained by the agent. We propose a systematic approach to current research in this field, which consists of three categories of me"},"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":"2301.10067","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-24T15:13:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9c22484763bc83ffca173d32c77a3efa3cf61993cb2e1f410d17b1f44c30acc3","abstract_canon_sha256":"6ebdd4fbfb809d232d94162cae2f9802ef79c3ca2d44b2f7bbeae6297415ac07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:35:37.552253Z","signature_b64":"1ipZ8zDnwhWjuxL6VA2C/w9Oab/tU+XC+aPY4CfhvJfueIOCEnrFSVlJRH6w6ACKxaT4V9DBj7TEBuK8pq3sBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"915212acf20e657025d819bed37c0f6e633a2732272e46c0abce27ddbca64934","last_reissued_at":"2026-07-05T05:35:37.551815Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:35:37.551815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Intrinsic Motivation in Model-based Reinforcement Learning: A Brief Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aleksandr I. Panov, Artem Latyshev","submitted_at":"2023-01-24T15:13:02Z","abstract_excerpt":"The reinforcement learning research area contains a wide range of methods for solving the problems of intelligent agent control. Despite the progress that has been made, the task of creating a highly autonomous agent is still a significant challenge. One potential solution to this problem is intrinsic motivation, a concept derived from developmental psychology. This review considers the existing methods for determining intrinsic motivation based on the world model obtained by the agent. We propose a systematic approach to current research in this field, which consists of three categories of me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.10067","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/2301.10067/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":"2301.10067","created_at":"2026-07-05T05:35:37.551886+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.10067v1","created_at":"2026-07-05T05:35:37.551886+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.10067","created_at":"2026-07-05T05:35:37.551886+00:00"},{"alias_kind":"pith_short_12","alias_value":"SFJBFLHSBZSX","created_at":"2026-07-05T05:35:37.551886+00:00"},{"alias_kind":"pith_short_16","alias_value":"SFJBFLHSBZSXAJOY","created_at":"2026-07-05T05:35:37.551886+00:00"},{"alias_kind":"pith_short_8","alias_value":"SFJBFLHS","created_at":"2026-07-05T05:35:37.551886+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.06139","citing_title":"Bounded Exploration with World Model Uncertainty in Soft Actor-Critic Reinforcement Learning Algorithm","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SFJBFLHSBZSXAJOYDG7NG7APNZ","json":"https://pith.science/pith/SFJBFLHSBZSXAJOYDG7NG7APNZ.json","graph_json":"https://pith.science/api/pith-number/SFJBFLHSBZSXAJOYDG7NG7APNZ/graph.json","events_json":"https://pith.science/api/pith-number/SFJBFLHSBZSXAJOYDG7NG7APNZ/events.json","paper":"https://pith.science/paper/SFJBFLHS"},"agent_actions":{"view_html":"https://pith.science/pith/SFJBFLHSBZSXAJOYDG7NG7APNZ","download_json":"https://pith.science/pith/SFJBFLHSBZSXAJOYDG7NG7APNZ.json","view_paper":"https://pith.science/paper/SFJBFLHS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.10067&json=true","fetch_graph":"https://pith.science/api/pith-number/SFJBFLHSBZSXAJOYDG7NG7APNZ/graph.json","fetch_events":"https://pith.science/api/pith-number/SFJBFLHSBZSXAJOYDG7NG7APNZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SFJBFLHSBZSXAJOYDG7NG7APNZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SFJBFLHSBZSXAJOYDG7NG7APNZ/action/storage_attestation","attest_author":"https://pith.science/pith/SFJBFLHSBZSXAJOYDG7NG7APNZ/action/author_attestation","sign_citation":"https://pith.science/pith/SFJBFLHSBZSXAJOYDG7NG7APNZ/action/citation_signature","submit_replication":"https://pith.science/pith/SFJBFLHSBZSXAJOYDG7NG7APNZ/action/replication_record"}},"created_at":"2026-07-05T05:35:37.551886+00:00","updated_at":"2026-07-05T05:35:37.551886+00:00"}