{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NFE7VJOJ6TUAYF6QKUHTS6WG6C","short_pith_number":"pith:NFE7VJOJ","schema_version":"1.0","canonical_sha256":"6949faa5c9f4e80c17d0550f397ac6f0bbc16ddbef4849a6febb4fa7a3764d28","source":{"kind":"arxiv","id":"2402.02429","version":3},"attestation_state":"computed","paper":{"title":"Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hai Zhang, Junqiao Zhao, Lanqing Li, Pheng-Ann Heng, Shatong Zhu, Xinyu Zhang, Yang Yu","submitted_at":"2024-02-04T09:58:42Z","abstract_excerpt":"As a marriage between offline RL and meta-RL, the advent of offline meta-reinforcement learning (OMRL) has shown great promise in enabling RL agents to multi-task and quickly adapt while acquiring knowledge safely. Among which, context-based OMRL (COMRL) as a popular paradigm, aims to learn a universal policy conditioned on effective task representations. In this work, by examining several key milestones in the field of COMRL, we propose to integrate these seemingly independent methodologies into a unified framework. Most importantly, we show that the pre-existing COMRL algorithms are essentia"},"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":"2402.02429","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-04T09:58:42Z","cross_cats_sorted":[],"title_canon_sha256":"df354fd644ef8283d57ba0308bf2a652b7a75e8115f913b0c59f09dba50b73ae","abstract_canon_sha256":"f65cb7c7d33f0c9efa51ba832e5c632436b193bcdba189b59b25147cc7fb7a02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:43.783165Z","signature_b64":"ozr0+CwcIRFrTv3+SexczvAAttPDrQSqw20HblMfRUVSulx1lNJz8FTWSBpZnziiKuUZze9Q5jisFq1Bq/osBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6949faa5c9f4e80c17d0550f397ac6f0bbc16ddbef4849a6febb4fa7a3764d28","last_reissued_at":"2026-07-05T09:59:43.782676Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:43.782676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hai Zhang, Junqiao Zhao, Lanqing Li, Pheng-Ann Heng, Shatong Zhu, Xinyu Zhang, Yang Yu","submitted_at":"2024-02-04T09:58:42Z","abstract_excerpt":"As a marriage between offline RL and meta-RL, the advent of offline meta-reinforcement learning (OMRL) has shown great promise in enabling RL agents to multi-task and quickly adapt while acquiring knowledge safely. Among which, context-based OMRL (COMRL) as a popular paradigm, aims to learn a universal policy conditioned on effective task representations. In this work, by examining several key milestones in the field of COMRL, we propose to integrate these seemingly independent methodologies into a unified framework. Most importantly, we show that the pre-existing COMRL algorithms are essentia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02429","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/2402.02429/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":"2402.02429","created_at":"2026-07-05T09:59:43.782742+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02429v3","created_at":"2026-07-05T09:59:43.782742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02429","created_at":"2026-07-05T09:59:43.782742+00:00"},{"alias_kind":"pith_short_12","alias_value":"NFE7VJOJ6TUA","created_at":"2026-07-05T09:59:43.782742+00:00"},{"alias_kind":"pith_short_16","alias_value":"NFE7VJOJ6TUAYF6Q","created_at":"2026-07-05T09:59:43.782742+00:00"},{"alias_kind":"pith_short_8","alias_value":"NFE7VJOJ","created_at":"2026-07-05T09:59:43.782742+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.16288","citing_title":"Next-Token Prediction Should be Ambiguity-Sensitive: A Meta-Learning Perspective","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NFE7VJOJ6TUAYF6QKUHTS6WG6C","json":"https://pith.science/pith/NFE7VJOJ6TUAYF6QKUHTS6WG6C.json","graph_json":"https://pith.science/api/pith-number/NFE7VJOJ6TUAYF6QKUHTS6WG6C/graph.json","events_json":"https://pith.science/api/pith-number/NFE7VJOJ6TUAYF6QKUHTS6WG6C/events.json","paper":"https://pith.science/paper/NFE7VJOJ"},"agent_actions":{"view_html":"https://pith.science/pith/NFE7VJOJ6TUAYF6QKUHTS6WG6C","download_json":"https://pith.science/pith/NFE7VJOJ6TUAYF6QKUHTS6WG6C.json","view_paper":"https://pith.science/paper/NFE7VJOJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02429&json=true","fetch_graph":"https://pith.science/api/pith-number/NFE7VJOJ6TUAYF6QKUHTS6WG6C/graph.json","fetch_events":"https://pith.science/api/pith-number/NFE7VJOJ6TUAYF6QKUHTS6WG6C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NFE7VJOJ6TUAYF6QKUHTS6WG6C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NFE7VJOJ6TUAYF6QKUHTS6WG6C/action/storage_attestation","attest_author":"https://pith.science/pith/NFE7VJOJ6TUAYF6QKUHTS6WG6C/action/author_attestation","sign_citation":"https://pith.science/pith/NFE7VJOJ6TUAYF6QKUHTS6WG6C/action/citation_signature","submit_replication":"https://pith.science/pith/NFE7VJOJ6TUAYF6QKUHTS6WG6C/action/replication_record"}},"created_at":"2026-07-05T09:59:43.782742+00:00","updated_at":"2026-07-05T09:59:43.782742+00:00"}