{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WEKSQVVOOA5KNRK4D2JF3T4EBG","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":"1ab910410bbaadcec84490559481eb6998365984a58ecd477237926969ff54d7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-18T08:50:30Z","title_canon_sha256":"09bbf33c5db0dc0120043f8f88ab3bed4da56d2f8ce2ed5e9ac4dfdb5fbbf210"},"schema_version":"1.0","source":{"id":"2403.11574","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.11574","created_at":"2026-07-05T09:29:14Z"},{"alias_kind":"arxiv_version","alias_value":"2403.11574v2","created_at":"2026-07-05T09:29:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11574","created_at":"2026-07-05T09:29:14Z"},{"alias_kind":"pith_short_12","alias_value":"WEKSQVVOOA5K","created_at":"2026-07-05T09:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"WEKSQVVOOA5KNRK4","created_at":"2026-07-05T09:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"WEKSQVVO","created_at":"2026-07-05T09:29:14Z"}],"graph_snapshots":[{"event_id":"sha256:bb478316def2b0f13a029d862f63b917af79d760033c475f44e5fa85afbb098e","target":"graph","created_at":"2026-07-05T09:29:14Z","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/2403.11574/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study offline multitask representation learning in reinforcement learning (RL), where a learner is provided with an offline dataset from different tasks that share a common representation and is asked to learn the shared representation. We theoretically investigate offline multitask low-rank RL, and propose a new algorithm called MORL for offline multitask representation learning. Furthermore, we examine downstream RL in reward-free, offline and online scenarios, where a new task is introduced to the agent that shares the same representation as the upstream offline tasks. Our theoretical re","authors_text":"Doina Precup, Haque Ishfaq, Mengdi Wang, Ming Yin, Raman Arora, Songtao Feng, Thanh Nguyen-Tang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-18T08:50:30Z","title":"Offline Multitask Representation Learning for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11574","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":"sha256:565dcee9c6c38680cbe739817984d36d4fbbf03cf3363669f4e48109d3be88dc","target":"record","created_at":"2026-07-05T09:29:14Z","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":"1ab910410bbaadcec84490559481eb6998365984a58ecd477237926969ff54d7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-18T08:50:30Z","title_canon_sha256":"09bbf33c5db0dc0120043f8f88ab3bed4da56d2f8ce2ed5e9ac4dfdb5fbbf210"},"schema_version":"1.0","source":{"id":"2403.11574","kind":"arxiv","version":2}},"canonical_sha256":"b1152856ae703aa6c55c1e925dcf8409947f1984e34500e4a04f13748c898113","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1152856ae703aa6c55c1e925dcf8409947f1984e34500e4a04f13748c898113","first_computed_at":"2026-07-05T09:29:14.097304Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:14.097304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T4H6x/KFs16fCRwvMXSlhktXb9JM7PTgeVY5NtpLa9oBVqtjX+uOUPCW8IQDCCvQw5gfFtolvziJTb62/ZmRBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:14.097854Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.11574","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:565dcee9c6c38680cbe739817984d36d4fbbf03cf3363669f4e48109d3be88dc","sha256:bb478316def2b0f13a029d862f63b917af79d760033c475f44e5fa85afbb098e"],"state_sha256":"6cc38f139017dae84c56e6704d650c9775d3fe8da5567ec370c325121d3630d2"}