{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PDQ5MAPV2M65YHFM2F4GQWZR42","short_pith_number":"pith:PDQ5MAPV","schema_version":"1.0","canonical_sha256":"78e1d601f5d33ddc1cacd178685b31e687f9a83495ffe83434747efa0a5974e8","source":{"kind":"arxiv","id":"2402.12570","version":1},"attestation_state":"computed","paper":{"title":"Offline Multi-task Transfer RL with Representational Penalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Avinandan Bose, Maryam Fazel, Simon Shaolei Du","submitted_at":"2024-02-19T21:52:44Z","abstract_excerpt":"We study the problem of representation transfer in offline Reinforcement Learning (RL), where a learner has access to episodic data from a number of source tasks collected a priori, and aims to learn a shared representation to be used in finding a good policy for a target task. Unlike in online RL where the agent interacts with the environment while learning a policy, in the offline setting there cannot be such interactions in either the source tasks or the target task; thus multi-task offline RL can suffer from incomplete coverage.\n  We propose an algorithm to compute pointwise uncertainty me"},"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":"2402.12570","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T21:52:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9d6f883b0982ee20b4a087bfcd19875598d310439647bfac5f30e3720c3ea4fe","abstract_canon_sha256":"98009a9b778accb864c8f8bde8b556508400d1daafbaa0f7291f197eb7adf307"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:13.093012Z","signature_b64":"bnsF2CkTvTsGoGDJo5yCB/e/QIMrVzW57IIPig7jCMy0bprXtuFRH6mYcb4juWdYUbMXgWmj07fnkgfqvc7nBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78e1d601f5d33ddc1cacd178685b31e687f9a83495ffe83434747efa0a5974e8","last_reissued_at":"2026-07-05T07:47:13.092524Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:13.092524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Offline Multi-task Transfer RL with Representational Penalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Avinandan Bose, Maryam Fazel, Simon Shaolei Du","submitted_at":"2024-02-19T21:52:44Z","abstract_excerpt":"We study the problem of representation transfer in offline Reinforcement Learning (RL), where a learner has access to episodic data from a number of source tasks collected a priori, and aims to learn a shared representation to be used in finding a good policy for a target task. Unlike in online RL where the agent interacts with the environment while learning a policy, in the offline setting there cannot be such interactions in either the source tasks or the target task; thus multi-task offline RL can suffer from incomplete coverage.\n  We propose an algorithm to compute pointwise uncertainty me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12570","kind":"arxiv","version":1},"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/2402.12570/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":"2402.12570","created_at":"2026-07-05T07:47:13.092582+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.12570v1","created_at":"2026-07-05T07:47:13.092582+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12570","created_at":"2026-07-05T07:47:13.092582+00:00"},{"alias_kind":"pith_short_12","alias_value":"PDQ5MAPV2M65","created_at":"2026-07-05T07:47:13.092582+00:00"},{"alias_kind":"pith_short_16","alias_value":"PDQ5MAPV2M65YHFM","created_at":"2026-07-05T07:47:13.092582+00:00"},{"alias_kind":"pith_short_8","alias_value":"PDQ5MAPV","created_at":"2026-07-05T07:47:13.092582+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PDQ5MAPV2M65YHFM2F4GQWZR42","json":"https://pith.science/pith/PDQ5MAPV2M65YHFM2F4GQWZR42.json","graph_json":"https://pith.science/api/pith-number/PDQ5MAPV2M65YHFM2F4GQWZR42/graph.json","events_json":"https://pith.science/api/pith-number/PDQ5MAPV2M65YHFM2F4GQWZR42/events.json","paper":"https://pith.science/paper/PDQ5MAPV"},"agent_actions":{"view_html":"https://pith.science/pith/PDQ5MAPV2M65YHFM2F4GQWZR42","download_json":"https://pith.science/pith/PDQ5MAPV2M65YHFM2F4GQWZR42.json","view_paper":"https://pith.science/paper/PDQ5MAPV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.12570&json=true","fetch_graph":"https://pith.science/api/pith-number/PDQ5MAPV2M65YHFM2F4GQWZR42/graph.json","fetch_events":"https://pith.science/api/pith-number/PDQ5MAPV2M65YHFM2F4GQWZR42/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PDQ5MAPV2M65YHFM2F4GQWZR42/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PDQ5MAPV2M65YHFM2F4GQWZR42/action/storage_attestation","attest_author":"https://pith.science/pith/PDQ5MAPV2M65YHFM2F4GQWZR42/action/author_attestation","sign_citation":"https://pith.science/pith/PDQ5MAPV2M65YHFM2F4GQWZR42/action/citation_signature","submit_replication":"https://pith.science/pith/PDQ5MAPV2M65YHFM2F4GQWZR42/action/replication_record"}},"created_at":"2026-07-05T07:47:13.092582+00:00","updated_at":"2026-07-05T07:47:13.092582+00:00"}