{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XM3BQN2X36QQHWLTJYQMZQPX4P","short_pith_number":"pith:XM3BQN2X","schema_version":"1.0","canonical_sha256":"bb36183757dfa103d9734e20ccc1f7e3d23197f9c5796fc60fa276b24bd7b177","source":{"kind":"arxiv","id":"2302.00935","version":4},"attestation_state":"computed","paper":{"title":"Policy Expansion for Bridging Offline-to-Online Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haichao Zhang, Haonan Yu, We Xu","submitted_at":"2023-02-02T08:25:12Z","abstract_excerpt":"Pre-training with offline data and online fine-tuning using reinforcement learning is a promising strategy for learning control policies by leveraging the best of both worlds in terms of sample efficiency and performance. One natural approach is to initialize the policy for online learning with the one trained offline. In this work, we introduce a policy expansion scheme for this task. After learning the offline policy, we use it as one candidate policy in a policy set. We then expand the policy set with another policy which will be responsible for further learning. The two policies will be co"},"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":"2302.00935","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-02-02T08:25:12Z","cross_cats_sorted":[],"title_canon_sha256":"e0b58cc79474f9348f6b3852f71193503238912e2653a0391258fba34ecc2759","abstract_canon_sha256":"9c0c43a8dc5b5c3e84a8c54b87dfbb7de38dcf4fc363ca4cfa26ac064c371f3a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:17.065821Z","signature_b64":"AZK1zbJU98rv81yMUmbdO027U5zFhIHNPnNJ4WHOW57BXFBBuo8flqvsDWsNsxayVqcdprK+mtVdh8NUg6RaAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb36183757dfa103d9734e20ccc1f7e3d23197f9c5796fc60fa276b24bd7b177","last_reissued_at":"2026-07-05T12:01:17.065122Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:17.065122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy Expansion for Bridging Offline-to-Online Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haichao Zhang, Haonan Yu, We Xu","submitted_at":"2023-02-02T08:25:12Z","abstract_excerpt":"Pre-training with offline data and online fine-tuning using reinforcement learning is a promising strategy for learning control policies by leveraging the best of both worlds in terms of sample efficiency and performance. One natural approach is to initialize the policy for online learning with the one trained offline. In this work, we introduce a policy expansion scheme for this task. After learning the offline policy, we use it as one candidate policy in a policy set. We then expand the policy set with another policy which will be responsible for further learning. The two policies will be co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.00935","kind":"arxiv","version":4},"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/2302.00935/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":"2302.00935","created_at":"2026-07-05T12:01:17.065211+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.00935v4","created_at":"2026-07-05T12:01:17.065211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.00935","created_at":"2026-07-05T12:01:17.065211+00:00"},{"alias_kind":"pith_short_12","alias_value":"XM3BQN2X36QQ","created_at":"2026-07-05T12:01:17.065211+00:00"},{"alias_kind":"pith_short_16","alias_value":"XM3BQN2X36QQHWLT","created_at":"2026-07-05T12:01:17.065211+00:00"},{"alias_kind":"pith_short_8","alias_value":"XM3BQN2X","created_at":"2026-07-05T12:01:17.065211+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14779","citing_title":"Peng's Q($\\lambda$) for Conservative Value Estimation in Offline Reinforcement Learning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18675","citing_title":"COOPO: Cyclic Offline-Online Policy Optimization Algorithm","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2507.07986","citing_title":"EXPO: Stable Reinforcement Learning with Expressive Policies","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XM3BQN2X36QQHWLTJYQMZQPX4P","json":"https://pith.science/pith/XM3BQN2X36QQHWLTJYQMZQPX4P.json","graph_json":"https://pith.science/api/pith-number/XM3BQN2X36QQHWLTJYQMZQPX4P/graph.json","events_json":"https://pith.science/api/pith-number/XM3BQN2X36QQHWLTJYQMZQPX4P/events.json","paper":"https://pith.science/paper/XM3BQN2X"},"agent_actions":{"view_html":"https://pith.science/pith/XM3BQN2X36QQHWLTJYQMZQPX4P","download_json":"https://pith.science/pith/XM3BQN2X36QQHWLTJYQMZQPX4P.json","view_paper":"https://pith.science/paper/XM3BQN2X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.00935&json=true","fetch_graph":"https://pith.science/api/pith-number/XM3BQN2X36QQHWLTJYQMZQPX4P/graph.json","fetch_events":"https://pith.science/api/pith-number/XM3BQN2X36QQHWLTJYQMZQPX4P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XM3BQN2X36QQHWLTJYQMZQPX4P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XM3BQN2X36QQHWLTJYQMZQPX4P/action/storage_attestation","attest_author":"https://pith.science/pith/XM3BQN2X36QQHWLTJYQMZQPX4P/action/author_attestation","sign_citation":"https://pith.science/pith/XM3BQN2X36QQHWLTJYQMZQPX4P/action/citation_signature","submit_replication":"https://pith.science/pith/XM3BQN2X36QQHWLTJYQMZQPX4P/action/replication_record"}},"created_at":"2026-07-05T12:01:17.065211+00:00","updated_at":"2026-07-05T12:01:17.065211+00:00"}