{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JVYTVPAQWVHEAWYOVAMWOOG33U","short_pith_number":"pith:JVYTVPAQ","schema_version":"1.0","canonical_sha256":"4d713abc10b54e405b0ea8196738dbdd24ae3aa4c1d1e0bbbb28eb178232bb7f","source":{"kind":"arxiv","id":"2402.18866","version":2},"attestation_state":"computed","paper":{"title":"Dr. Strategy: Model-Based Generalist Agents with Strategic Dreaming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dongyeong Kim, Hany Hamed, Jaesik Yoon, Subin Kim, Sungjin Ahn","submitted_at":"2024-02-29T05:34:05Z","abstract_excerpt":"Model-based reinforcement learning (MBRL) has been a primary approach to ameliorating the sample efficiency issue as well as to make a generalist agent. However, there has not been much effort toward enhancing the strategy of dreaming itself. Therefore, it is a question whether and how an agent can \"dream better\" in a more structured and strategic way. In this paper, inspired by the observation from cognitive science suggesting that humans use a spatial divide-and-conquer strategy in planning, we propose a new MBRL agent, called Dr. Strategy, which is equipped with a novel Dreaming Strategy. T"},"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":"2402.18866","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-29T05:34:05Z","cross_cats_sorted":[],"title_canon_sha256":"6eea4744f6f979f0b7381209cb8a2bf82333904a0558d3a4b0153deb2af1ae97","abstract_canon_sha256":"483eef0cede09427969caea1a593cd6d28e1b89c6f5d854d6b6ce45cf989183b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:05.126973Z","signature_b64":"8/N2XpNm9i6IyNjpojhh/hk7bblgM1QZcz8U7V/qBNWbcEehW8GdVE3tLQy7Wjt6///4sC5WbM7Rt+tYWAxRBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d713abc10b54e405b0ea8196738dbdd24ae3aa4c1d1e0bbbb28eb178232bb7f","last_reissued_at":"2026-07-05T08:27:05.126551Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:05.126551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dr. Strategy: Model-Based Generalist Agents with Strategic Dreaming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dongyeong Kim, Hany Hamed, Jaesik Yoon, Subin Kim, Sungjin Ahn","submitted_at":"2024-02-29T05:34:05Z","abstract_excerpt":"Model-based reinforcement learning (MBRL) has been a primary approach to ameliorating the sample efficiency issue as well as to make a generalist agent. However, there has not been much effort toward enhancing the strategy of dreaming itself. Therefore, it is a question whether and how an agent can \"dream better\" in a more structured and strategic way. In this paper, inspired by the observation from cognitive science suggesting that humans use a spatial divide-and-conquer strategy in planning, we propose a new MBRL agent, called Dr. Strategy, which is equipped with a novel Dreaming Strategy. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18866","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.18866/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":"2402.18866","created_at":"2026-07-05T08:27:05.126608+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.18866v2","created_at":"2026-07-05T08:27:05.126608+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18866","created_at":"2026-07-05T08:27:05.126608+00:00"},{"alias_kind":"pith_short_12","alias_value":"JVYTVPAQWVHE","created_at":"2026-07-05T08:27:05.126608+00:00"},{"alias_kind":"pith_short_16","alias_value":"JVYTVPAQWVHEAWYO","created_at":"2026-07-05T08:27:05.126608+00:00"},{"alias_kind":"pith_short_8","alias_value":"JVYTVPAQ","created_at":"2026-07-05T08:27:05.126608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.02774","citing_title":"Learn A Flexible Exploration Model for Parameterized Action Markov Decision Processes","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JVYTVPAQWVHEAWYOVAMWOOG33U","json":"https://pith.science/pith/JVYTVPAQWVHEAWYOVAMWOOG33U.json","graph_json":"https://pith.science/api/pith-number/JVYTVPAQWVHEAWYOVAMWOOG33U/graph.json","events_json":"https://pith.science/api/pith-number/JVYTVPAQWVHEAWYOVAMWOOG33U/events.json","paper":"https://pith.science/paper/JVYTVPAQ"},"agent_actions":{"view_html":"https://pith.science/pith/JVYTVPAQWVHEAWYOVAMWOOG33U","download_json":"https://pith.science/pith/JVYTVPAQWVHEAWYOVAMWOOG33U.json","view_paper":"https://pith.science/paper/JVYTVPAQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.18866&json=true","fetch_graph":"https://pith.science/api/pith-number/JVYTVPAQWVHEAWYOVAMWOOG33U/graph.json","fetch_events":"https://pith.science/api/pith-number/JVYTVPAQWVHEAWYOVAMWOOG33U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JVYTVPAQWVHEAWYOVAMWOOG33U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JVYTVPAQWVHEAWYOVAMWOOG33U/action/storage_attestation","attest_author":"https://pith.science/pith/JVYTVPAQWVHEAWYOVAMWOOG33U/action/author_attestation","sign_citation":"https://pith.science/pith/JVYTVPAQWVHEAWYOVAMWOOG33U/action/citation_signature","submit_replication":"https://pith.science/pith/JVYTVPAQWVHEAWYOVAMWOOG33U/action/replication_record"}},"created_at":"2026-07-05T08:27:05.126608+00:00","updated_at":"2026-07-05T08:27:05.126608+00:00"}