{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JVYTVPAQWVHEAWYOVAMWOOG33U","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":"483eef0cede09427969caea1a593cd6d28e1b89c6f5d854d6b6ce45cf989183b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-29T05:34:05Z","title_canon_sha256":"6eea4744f6f979f0b7381209cb8a2bf82333904a0558d3a4b0153deb2af1ae97"},"schema_version":"1.0","source":{"id":"2402.18866","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.18866","created_at":"2026-07-05T08:27:05Z"},{"alias_kind":"arxiv_version","alias_value":"2402.18866v2","created_at":"2026-07-05T08:27:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18866","created_at":"2026-07-05T08:27:05Z"},{"alias_kind":"pith_short_12","alias_value":"JVYTVPAQWVHE","created_at":"2026-07-05T08:27:05Z"},{"alias_kind":"pith_short_16","alias_value":"JVYTVPAQWVHEAWYO","created_at":"2026-07-05T08:27:05Z"},{"alias_kind":"pith_short_8","alias_value":"JVYTVPAQ","created_at":"2026-07-05T08:27:05Z"}],"graph_snapshots":[{"event_id":"sha256:d47d55b3340e54172756241a282ccab1235cdb0ea41b2acb4c40617a04595b1e","target":"graph","created_at":"2026-07-05T08:27:05Z","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/2402.18866/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dongyeong Kim, Hany Hamed, Jaesik Yoon, Subin Kim, Sungjin Ahn","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-29T05:34:05Z","title":"Dr. Strategy: Model-Based Generalist Agents with Strategic Dreaming"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18866","kind":"arxiv","version":2},"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":"sha256:543867c742ea4d3d89a0781ad7a7168674c6ff09859b806ad9e0cf697bff7542","target":"record","created_at":"2026-07-05T08:27:05Z","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":"483eef0cede09427969caea1a593cd6d28e1b89c6f5d854d6b6ce45cf989183b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-29T05:34:05Z","title_canon_sha256":"6eea4744f6f979f0b7381209cb8a2bf82333904a0558d3a4b0153deb2af1ae97"},"schema_version":"1.0","source":{"id":"2402.18866","kind":"arxiv","version":2}},"canonical_sha256":"4d713abc10b54e405b0ea8196738dbdd24ae3aa4c1d1e0bbbb28eb178232bb7f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d713abc10b54e405b0ea8196738dbdd24ae3aa4c1d1e0bbbb28eb178232bb7f","first_computed_at":"2026-07-05T08:27:05.126551Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:05.126551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8/N2XpNm9i6IyNjpojhh/hk7bblgM1QZcz8U7V/qBNWbcEehW8GdVE3tLQy7Wjt6///4sC5WbM7Rt+tYWAxRBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:05.126973Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.18866","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:543867c742ea4d3d89a0781ad7a7168674c6ff09859b806ad9e0cf697bff7542","sha256:d47d55b3340e54172756241a282ccab1235cdb0ea41b2acb4c40617a04595b1e"],"state_sha256":"39a416f6a0588b3b5f3014515277cf99684c5acdf076b9f13dba28fea0e1a3c1"}