{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:LJYR2RANSRVAEIM52I4ME26CKO","short_pith_number":"pith:LJYR2RAN","canonical_record":{"source":{"id":"2210.06718","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-13T04:19:05Z","cross_cats_sorted":[],"title_canon_sha256":"2b4c1f3b9afe5424c93d518c7d2b0dd9c6f1d3236a26ecac497c08b916891e17","abstract_canon_sha256":"e12c3b2602e810db2869e3c644caf259e5b9664d7201f53d205dc97b8d89bca3"},"schema_version":"1.0"},"canonical_sha256":"5a711d440d946a02219dd238c26bc2539653cf566f75512c9c7c08458bdabc6a","source":{"kind":"arxiv","id":"2210.06718","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.06718","created_at":"2026-07-05T05:50:09Z"},{"alias_kind":"arxiv_version","alias_value":"2210.06718v3","created_at":"2026-07-05T05:50:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.06718","created_at":"2026-07-05T05:50:09Z"},{"alias_kind":"pith_short_12","alias_value":"LJYR2RANSRVA","created_at":"2026-07-05T05:50:09Z"},{"alias_kind":"pith_short_16","alias_value":"LJYR2RANSRVAEIM5","created_at":"2026-07-05T05:50:09Z"},{"alias_kind":"pith_short_8","alias_value":"LJYR2RAN","created_at":"2026-07-05T05:50:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:LJYR2RANSRVAEIM52I4ME26CKO","target":"record","payload":{"canonical_record":{"source":{"id":"2210.06718","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-13T04:19:05Z","cross_cats_sorted":[],"title_canon_sha256":"2b4c1f3b9afe5424c93d518c7d2b0dd9c6f1d3236a26ecac497c08b916891e17","abstract_canon_sha256":"e12c3b2602e810db2869e3c644caf259e5b9664d7201f53d205dc97b8d89bca3"},"schema_version":"1.0"},"canonical_sha256":"5a711d440d946a02219dd238c26bc2539653cf566f75512c9c7c08458bdabc6a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:50:09.560881Z","signature_b64":"fMcLDkFOGiRloAjrm4PvtyfxYRagqwtgS/Bt65OP/nGNqmZy4eXGSaXdtjIch4eKu4oq+k5Cav9Hq2bHdA/BBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a711d440d946a02219dd238c26bc2539653cf566f75512c9c7c08458bdabc6a","last_reissued_at":"2026-07-05T05:50:09.560270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:50:09.560270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.06718","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:50:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZOBPPk08BlHqCQQDUdJAQTpc7tG9fshw+8ooZnePOvA0fSVgILrzq9y1k6/nQMRAdMU3aMbo6j8akd7uP4fiAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T02:30:49.406367Z"},"content_sha256":"aa2ef80764689406949af3695a83f0a67893c099ce96ef4cc4a1aed6f170260f","schema_version":"1.0","event_id":"sha256:aa2ef80764689406949af3695a83f0a67893c099ce96ef4cc4a1aed6f170260f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:LJYR2RANSRVAEIM52I4ME26CKO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Akshay Krishnamurthy, Ayush Sekhari, J. Andrew Bagnell, Wen Sun, Yifei Zhou, Yuda Song","submitted_at":"2022-10-13T04:19:05Z","abstract_excerpt":"We consider a hybrid reinforcement learning setting (Hybrid RL), in which an agent has access to an offline dataset and the ability to collect experience via real-world online interaction. The framework mitigates the challenges that arise in both pure offline and online RL settings, allowing for the design of simple and highly effective algorithms, in both theory and practice. We demonstrate these advantages by adapting the classical Q learning/iteration algorithm to the hybrid setting, which we call Hybrid Q-Learning or Hy-Q. In our theoretical results, we prove that the algorithm is both com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.06718","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/2210.06718/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:50:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Vw4zXtZTY9arezul5qCoU1Pg4r22DoT0vkBg6dM44eQzeyJASpZcNHg2v+LsvHNT5wJKUB4muLWQhu2gWhFBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T02:30:49.406863Z"},"content_sha256":"b5f1b7898af91a91514ddddf47188508cebcfd52880b6c466142ab7b73535495","schema_version":"1.0","event_id":"sha256:b5f1b7898af91a91514ddddf47188508cebcfd52880b6c466142ab7b73535495"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LJYR2RANSRVAEIM52I4ME26CKO/bundle.json","state_url":"https://pith.science/pith/LJYR2RANSRVAEIM52I4ME26CKO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LJYR2RANSRVAEIM52I4ME26CKO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T02:30:49Z","links":{"resolver":"https://pith.science/pith/LJYR2RANSRVAEIM52I4ME26CKO","bundle":"https://pith.science/pith/LJYR2RANSRVAEIM52I4ME26CKO/bundle.json","state":"https://pith.science/pith/LJYR2RANSRVAEIM52I4ME26CKO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LJYR2RANSRVAEIM52I4ME26CKO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LJYR2RANSRVAEIM52I4ME26CKO","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":"e12c3b2602e810db2869e3c644caf259e5b9664d7201f53d205dc97b8d89bca3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-13T04:19:05Z","title_canon_sha256":"2b4c1f3b9afe5424c93d518c7d2b0dd9c6f1d3236a26ecac497c08b916891e17"},"schema_version":"1.0","source":{"id":"2210.06718","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.06718","created_at":"2026-07-05T05:50:09Z"},{"alias_kind":"arxiv_version","alias_value":"2210.06718v3","created_at":"2026-07-05T05:50:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.06718","created_at":"2026-07-05T05:50:09Z"},{"alias_kind":"pith_short_12","alias_value":"LJYR2RANSRVA","created_at":"2026-07-05T05:50:09Z"},{"alias_kind":"pith_short_16","alias_value":"LJYR2RANSRVAEIM5","created_at":"2026-07-05T05:50:09Z"},{"alias_kind":"pith_short_8","alias_value":"LJYR2RAN","created_at":"2026-07-05T05:50:09Z"}],"graph_snapshots":[{"event_id":"sha256:b5f1b7898af91a91514ddddf47188508cebcfd52880b6c466142ab7b73535495","target":"graph","created_at":"2026-07-05T05:50:09Z","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/2210.06718/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider a hybrid reinforcement learning setting (Hybrid RL), in which an agent has access to an offline dataset and the ability to collect experience via real-world online interaction. The framework mitigates the challenges that arise in both pure offline and online RL settings, allowing for the design of simple and highly effective algorithms, in both theory and practice. We demonstrate these advantages by adapting the classical Q learning/iteration algorithm to the hybrid setting, which we call Hybrid Q-Learning or Hy-Q. In our theoretical results, we prove that the algorithm is both com","authors_text":"Akshay Krishnamurthy, Ayush Sekhari, J. Andrew Bagnell, Wen Sun, Yifei Zhou, Yuda Song","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-13T04:19:05Z","title":"Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.06718","kind":"arxiv","version":3},"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:aa2ef80764689406949af3695a83f0a67893c099ce96ef4cc4a1aed6f170260f","target":"record","created_at":"2026-07-05T05:50:09Z","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":"e12c3b2602e810db2869e3c644caf259e5b9664d7201f53d205dc97b8d89bca3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-13T04:19:05Z","title_canon_sha256":"2b4c1f3b9afe5424c93d518c7d2b0dd9c6f1d3236a26ecac497c08b916891e17"},"schema_version":"1.0","source":{"id":"2210.06718","kind":"arxiv","version":3}},"canonical_sha256":"5a711d440d946a02219dd238c26bc2539653cf566f75512c9c7c08458bdabc6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a711d440d946a02219dd238c26bc2539653cf566f75512c9c7c08458bdabc6a","first_computed_at":"2026-07-05T05:50:09.560270Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:50:09.560270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fMcLDkFOGiRloAjrm4PvtyfxYRagqwtgS/Bt65OP/nGNqmZy4eXGSaXdtjIch4eKu4oq+k5Cav9Hq2bHdA/BBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:50:09.560881Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.06718","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa2ef80764689406949af3695a83f0a67893c099ce96ef4cc4a1aed6f170260f","sha256:b5f1b7898af91a91514ddddf47188508cebcfd52880b6c466142ab7b73535495"],"state_sha256":"0aeea4eab0bd65d2f73c45d9ae207915253a4c6e2761b70dc4be3966d2e5f06b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"laLQQSbsrzOw29GLSyt+kP5+K/sRvLE9EJyauZxNu/WnWv8dBtob+IfDNtHfSVdWyg53qbtbvXB5feUKMp43Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T02:30:49.412281Z","bundle_sha256":"9547986b820d57cf29b78435c8e7c3b00be3010a25ae3589f1e0259248765b35"}}