{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OVOXQ67QF337UAVUYRMV3VKI55","short_pith_number":"pith:OVOXQ67Q","schema_version":"1.0","canonical_sha256":"755d787bf02ef7fa02b4c4595dd548ef4548bcc5cbc4953c744896ae4e53b040","source":{"kind":"arxiv","id":"2401.08478","version":2},"attestation_state":"computed","paper":{"title":"Solving Continual Offline Reinforcement Learning with Decision Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chen Zhao, Chun Yuan, Dacheng Tao, Kaixin Huang, Li Shen","submitted_at":"2024-01-16T16:28:32Z","abstract_excerpt":"Continuous offline reinforcement learning (CORL) combines continuous and offline reinforcement learning, enabling agents to learn multiple tasks from static datasets without forgetting prior tasks. However, CORL faces challenges in balancing stability and plasticity. Existing methods, employing Actor-Critic structures and experience replay (ER), suffer from distribution shifts, low efficiency, and weak knowledge-sharing. We aim to investigate whether Decision Transformer (DT), another offline RL paradigm, can serve as a more suitable offline continuous learner to address these issues. We first"},"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":"2401.08478","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-16T16:28:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a9c2102d521d594e4dbda11c8169c921d2e549d1b496f929e43b0889fb968518","abstract_canon_sha256":"09d7c3f692df14911d80dc3ea903f8fe745f06ca80e316393d014180485f6dd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:09.303043Z","signature_b64":"aW9DAxMdR+lYhAdXIkdPL/xrkwSkFHEDPYX3uAuQfPN9VyC5cXyks9ZM3+WpBUnmcprXWIVyWEgFrO8IbVqBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"755d787bf02ef7fa02b4c4595dd548ef4548bcc5cbc4953c744896ae4e53b040","last_reissued_at":"2026-07-05T08:05:09.302603Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:09.302603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solving Continual Offline Reinforcement Learning with Decision Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chen Zhao, Chun Yuan, Dacheng Tao, Kaixin Huang, Li Shen","submitted_at":"2024-01-16T16:28:32Z","abstract_excerpt":"Continuous offline reinforcement learning (CORL) combines continuous and offline reinforcement learning, enabling agents to learn multiple tasks from static datasets without forgetting prior tasks. However, CORL faces challenges in balancing stability and plasticity. Existing methods, employing Actor-Critic structures and experience replay (ER), suffer from distribution shifts, low efficiency, and weak knowledge-sharing. We aim to investigate whether Decision Transformer (DT), another offline RL paradigm, can serve as a more suitable offline continuous learner to address these issues. We first"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08478","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/2401.08478/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":"2401.08478","created_at":"2026-07-05T08:05:09.302663+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.08478v2","created_at":"2026-07-05T08:05:09.302663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08478","created_at":"2026-07-05T08:05:09.302663+00:00"},{"alias_kind":"pith_short_12","alias_value":"OVOXQ67QF337","created_at":"2026-07-05T08:05:09.302663+00:00"},{"alias_kind":"pith_short_16","alias_value":"OVOXQ67QF337UAVU","created_at":"2026-07-05T08:05:09.302663+00:00"},{"alias_kind":"pith_short_8","alias_value":"OVOXQ67Q","created_at":"2026-07-05T08:05:09.302663+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":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OVOXQ67QF337UAVUYRMV3VKI55","json":"https://pith.science/pith/OVOXQ67QF337UAVUYRMV3VKI55.json","graph_json":"https://pith.science/api/pith-number/OVOXQ67QF337UAVUYRMV3VKI55/graph.json","events_json":"https://pith.science/api/pith-number/OVOXQ67QF337UAVUYRMV3VKI55/events.json","paper":"https://pith.science/paper/OVOXQ67Q"},"agent_actions":{"view_html":"https://pith.science/pith/OVOXQ67QF337UAVUYRMV3VKI55","download_json":"https://pith.science/pith/OVOXQ67QF337UAVUYRMV3VKI55.json","view_paper":"https://pith.science/paper/OVOXQ67Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.08478&json=true","fetch_graph":"https://pith.science/api/pith-number/OVOXQ67QF337UAVUYRMV3VKI55/graph.json","fetch_events":"https://pith.science/api/pith-number/OVOXQ67QF337UAVUYRMV3VKI55/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OVOXQ67QF337UAVUYRMV3VKI55/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OVOXQ67QF337UAVUYRMV3VKI55/action/storage_attestation","attest_author":"https://pith.science/pith/OVOXQ67QF337UAVUYRMV3VKI55/action/author_attestation","sign_citation":"https://pith.science/pith/OVOXQ67QF337UAVUYRMV3VKI55/action/citation_signature","submit_replication":"https://pith.science/pith/OVOXQ67QF337UAVUYRMV3VKI55/action/replication_record"}},"created_at":"2026-07-05T08:05:09.302663+00:00","updated_at":"2026-07-05T08:05:09.302663+00:00"}