{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QUZEHKJFOW4XREBJU6NHTBZJLR","short_pith_number":"pith:QUZEHKJF","schema_version":"1.0","canonical_sha256":"853243a92575b9789029a79a7987295c7137bb1047dc3941f0ce7544f4b1ebfe","source":{"kind":"arxiv","id":"2401.16650","version":3},"attestation_state":"computed","paper":{"title":"Augmenting Replay in World Models for Continual Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gideon Kowadlo, Levin Kuhlmann, Luke Yang","submitted_at":"2024-01-30T00:48:26Z","abstract_excerpt":"Continual RL requires an agent to learn new tasks without forgetting previous ones, while improving on both past and future tasks. The most common approaches use model-free algorithms and replay buffers can help to mitigate catastrophic forgetting, but often struggle with scalability due to large memory requirements. Biologically inspired replay suggests replay to a world model, aligning with model-based RL; as opposed to the common setting of replay in model-free algorithms. Model-based RL offers benefits for continual RL by leveraging knowledge of the environment, independent of policy. We i"},"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":"2401.16650","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-30T00:48:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9785176195efe6f53f3eabc2a913266c7cb4a9aa14fb82774b507888053f1fa1","abstract_canon_sha256":"2dc4ba64bdf61f1019abce9f3f68ab18cadaad9de9ec543baabacd6c645388e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:11.696200Z","signature_b64":"yfFFLJGT3YEB4AGqMnf9SKMVGVBuei+pdBDKup5S3uSirTTHjehmD2eRpcMM1HlxQaJpREs0mvcVHfaXML9LBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"853243a92575b9789029a79a7987295c7137bb1047dc3941f0ce7544f4b1ebfe","last_reissued_at":"2026-07-05T08:44:11.695714Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:11.695714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Augmenting Replay in World Models for Continual Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gideon Kowadlo, Levin Kuhlmann, Luke Yang","submitted_at":"2024-01-30T00:48:26Z","abstract_excerpt":"Continual RL requires an agent to learn new tasks without forgetting previous ones, while improving on both past and future tasks. The most common approaches use model-free algorithms and replay buffers can help to mitigate catastrophic forgetting, but often struggle with scalability due to large memory requirements. Biologically inspired replay suggests replay to a world model, aligning with model-based RL; as opposed to the common setting of replay in model-free algorithms. Model-based RL offers benefits for continual RL by leveraging knowledge of the environment, independent of policy. We i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16650","kind":"arxiv","version":3},"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/2401.16650/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":"2401.16650","created_at":"2026-07-05T08:44:11.695772+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.16650v3","created_at":"2026-07-05T08:44:11.695772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16650","created_at":"2026-07-05T08:44:11.695772+00:00"},{"alias_kind":"pith_short_12","alias_value":"QUZEHKJFOW4X","created_at":"2026-07-05T08:44:11.695772+00:00"},{"alias_kind":"pith_short_16","alias_value":"QUZEHKJFOW4XREBJ","created_at":"2026-07-05T08:44:11.695772+00:00"},{"alias_kind":"pith_short_8","alias_value":"QUZEHKJF","created_at":"2026-07-05T08:44:11.695772+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.11395","citing_title":"ARROW: Augmented Replay for RObust World models","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QUZEHKJFOW4XREBJU6NHTBZJLR","json":"https://pith.science/pith/QUZEHKJFOW4XREBJU6NHTBZJLR.json","graph_json":"https://pith.science/api/pith-number/QUZEHKJFOW4XREBJU6NHTBZJLR/graph.json","events_json":"https://pith.science/api/pith-number/QUZEHKJFOW4XREBJU6NHTBZJLR/events.json","paper":"https://pith.science/paper/QUZEHKJF"},"agent_actions":{"view_html":"https://pith.science/pith/QUZEHKJFOW4XREBJU6NHTBZJLR","download_json":"https://pith.science/pith/QUZEHKJFOW4XREBJU6NHTBZJLR.json","view_paper":"https://pith.science/paper/QUZEHKJF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.16650&json=true","fetch_graph":"https://pith.science/api/pith-number/QUZEHKJFOW4XREBJU6NHTBZJLR/graph.json","fetch_events":"https://pith.science/api/pith-number/QUZEHKJFOW4XREBJU6NHTBZJLR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QUZEHKJFOW4XREBJU6NHTBZJLR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QUZEHKJFOW4XREBJU6NHTBZJLR/action/storage_attestation","attest_author":"https://pith.science/pith/QUZEHKJFOW4XREBJU6NHTBZJLR/action/author_attestation","sign_citation":"https://pith.science/pith/QUZEHKJFOW4XREBJU6NHTBZJLR/action/citation_signature","submit_replication":"https://pith.science/pith/QUZEHKJFOW4XREBJU6NHTBZJLR/action/replication_record"}},"created_at":"2026-07-05T08:44:11.695772+00:00","updated_at":"2026-07-05T08:44:11.695772+00:00"}