{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TFBUBL3R2DPNQGK2F4V4ZVW2ZN","short_pith_number":"pith:TFBUBL3R","schema_version":"1.0","canonical_sha256":"994340af71d0ded8195a2f2bccd6dacb744f06568d4d1c4f73d4c8d12491a3b9","source":{"kind":"arxiv","id":"2404.12639","version":3},"attestation_state":"computed","paper":{"title":"Data-Incremental Continual Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Donglin Wang, Sibo Gai","submitted_at":"2024-04-19T05:45:43Z","abstract_excerpt":"In this work, we propose a new setting of continual learning: data-incremental continual offline reinforcement learning (DICORL), in which an agent is asked to learn a sequence of datasets of a single offline reinforcement learning (RL) task continually, instead of learning a sequence of offline RL tasks with respective datasets. Then, we propose that this new setting will introduce a unique challenge to continual learning: active forgetting, which means that the agent will forget the learnt skill actively. The main reason for active forgetting is conservative learning used by offline RL, whic"},"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":"2404.12639","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-19T05:45:43Z","cross_cats_sorted":[],"title_canon_sha256":"5bc13cec46323e21251b3efcec0fda499a10bdc834cdd8b55db193f8f43e04c9","abstract_canon_sha256":"1ea1047a947ad633e44e09f92af0d2782b256be2f1a86c5ddd2b4098395d47a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:42.238698Z","signature_b64":"1G6K7scv3Fogbh9rOlErAd/mdnPQyTEdeUteSH40A9AsZtLk4JvRfuYWotG35s1WxVetE6K7LV9gaqy7/yulDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"994340af71d0ded8195a2f2bccd6dacb744f06568d4d1c4f73d4c8d12491a3b9","last_reissued_at":"2026-07-05T09:49:42.238040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:42.238040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Incremental Continual Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Donglin Wang, Sibo Gai","submitted_at":"2024-04-19T05:45:43Z","abstract_excerpt":"In this work, we propose a new setting of continual learning: data-incremental continual offline reinforcement learning (DICORL), in which an agent is asked to learn a sequence of datasets of a single offline reinforcement learning (RL) task continually, instead of learning a sequence of offline RL tasks with respective datasets. Then, we propose that this new setting will introduce a unique challenge to continual learning: active forgetting, which means that the agent will forget the learnt skill actively. The main reason for active forgetting is conservative learning used by offline RL, whic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12639","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/2404.12639/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":"2404.12639","created_at":"2026-07-05T09:49:42.238197+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.12639v3","created_at":"2026-07-05T09:49:42.238197+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12639","created_at":"2026-07-05T09:49:42.238197+00:00"},{"alias_kind":"pith_short_12","alias_value":"TFBUBL3R2DPN","created_at":"2026-07-05T09:49:42.238197+00:00"},{"alias_kind":"pith_short_16","alias_value":"TFBUBL3R2DPNQGK2","created_at":"2026-07-05T09:49:42.238197+00:00"},{"alias_kind":"pith_short_8","alias_value":"TFBUBL3R","created_at":"2026-07-05T09:49:42.238197+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05932","citing_title":"Skill Expansion and Composition in Parameter Space","ref_index":2020,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TFBUBL3R2DPNQGK2F4V4ZVW2ZN","json":"https://pith.science/pith/TFBUBL3R2DPNQGK2F4V4ZVW2ZN.json","graph_json":"https://pith.science/api/pith-number/TFBUBL3R2DPNQGK2F4V4ZVW2ZN/graph.json","events_json":"https://pith.science/api/pith-number/TFBUBL3R2DPNQGK2F4V4ZVW2ZN/events.json","paper":"https://pith.science/paper/TFBUBL3R"},"agent_actions":{"view_html":"https://pith.science/pith/TFBUBL3R2DPNQGK2F4V4ZVW2ZN","download_json":"https://pith.science/pith/TFBUBL3R2DPNQGK2F4V4ZVW2ZN.json","view_paper":"https://pith.science/paper/TFBUBL3R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.12639&json=true","fetch_graph":"https://pith.science/api/pith-number/TFBUBL3R2DPNQGK2F4V4ZVW2ZN/graph.json","fetch_events":"https://pith.science/api/pith-number/TFBUBL3R2DPNQGK2F4V4ZVW2ZN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TFBUBL3R2DPNQGK2F4V4ZVW2ZN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TFBUBL3R2DPNQGK2F4V4ZVW2ZN/action/storage_attestation","attest_author":"https://pith.science/pith/TFBUBL3R2DPNQGK2F4V4ZVW2ZN/action/author_attestation","sign_citation":"https://pith.science/pith/TFBUBL3R2DPNQGK2F4V4ZVW2ZN/action/citation_signature","submit_replication":"https://pith.science/pith/TFBUBL3R2DPNQGK2F4V4ZVW2ZN/action/replication_record"}},"created_at":"2026-07-05T09:49:42.238197+00:00","updated_at":"2026-07-05T09:49:42.238197+00:00"}