{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:K6TVQ27DWXPLHKMKG4QQS7PQOG","short_pith_number":"pith:K6TVQ27D","schema_version":"1.0","canonical_sha256":"57a7586be3b5deb3a98a3721097df071a8ad7e44c355fa3dd0f786f196008ebb","source":{"kind":"arxiv","id":"2210.12160","version":4},"attestation_state":"computed","paper":{"title":"On the connection between Bregman divergence and value in regularized Markov decision processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Brendan O'Donoghue","submitted_at":"2022-10-21T15:28:30Z","abstract_excerpt":"In this short note we derive a relationship between the Bregman divergence from the current policy to the optimal policy and the suboptimality of the current value function in a regularized Markov decision process. This result has implications for multi-task reinforcement learning, offline reinforcement learning, and regret analysis under function approximation, among others."},"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":"2210.12160","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-21T15:28:30Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"f906a746e7f2ee969f19b4550e44b5b1d5e6b640a31a57f631a40da4bc6be975","abstract_canon_sha256":"20301f7b20f1c06841310de41cc37ec493ea1991d0decca079f30b733c078845"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:39.101653Z","signature_b64":"yUHNo0Mmrn84e1+x55dy86DJTFbTdBT4MtNTw9HpRJ+R3lHixadmiYm8a8nl6DKFgawInaLnbdgpaQbBzGuuBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57a7586be3b5deb3a98a3721097df071a8ad7e44c355fa3dd0f786f196008ebb","last_reissued_at":"2026-07-05T05:13:39.101135Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:39.101135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the connection between Bregman divergence and value in regularized Markov decision processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Brendan O'Donoghue","submitted_at":"2022-10-21T15:28:30Z","abstract_excerpt":"In this short note we derive a relationship between the Bregman divergence from the current policy to the optimal policy and the suboptimality of the current value function in a regularized Markov decision process. This result has implications for multi-task reinforcement learning, offline reinforcement learning, and regret analysis under function approximation, among others."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.12160","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/2210.12160/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":"2210.12160","created_at":"2026-07-05T05:13:39.101206+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.12160v4","created_at":"2026-07-05T05:13:39.101206+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12160","created_at":"2026-07-05T05:13:39.101206+00:00"},{"alias_kind":"pith_short_12","alias_value":"K6TVQ27DWXPL","created_at":"2026-07-05T05:13:39.101206+00:00"},{"alias_kind":"pith_short_16","alias_value":"K6TVQ27DWXPLHKMK","created_at":"2026-07-05T05:13:39.101206+00:00"},{"alias_kind":"pith_short_8","alias_value":"K6TVQ27D","created_at":"2026-07-05T05:13:39.101206+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/K6TVQ27DWXPLHKMKG4QQS7PQOG","json":"https://pith.science/pith/K6TVQ27DWXPLHKMKG4QQS7PQOG.json","graph_json":"https://pith.science/api/pith-number/K6TVQ27DWXPLHKMKG4QQS7PQOG/graph.json","events_json":"https://pith.science/api/pith-number/K6TVQ27DWXPLHKMKG4QQS7PQOG/events.json","paper":"https://pith.science/paper/K6TVQ27D"},"agent_actions":{"view_html":"https://pith.science/pith/K6TVQ27DWXPLHKMKG4QQS7PQOG","download_json":"https://pith.science/pith/K6TVQ27DWXPLHKMKG4QQS7PQOG.json","view_paper":"https://pith.science/paper/K6TVQ27D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.12160&json=true","fetch_graph":"https://pith.science/api/pith-number/K6TVQ27DWXPLHKMKG4QQS7PQOG/graph.json","fetch_events":"https://pith.science/api/pith-number/K6TVQ27DWXPLHKMKG4QQS7PQOG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K6TVQ27DWXPLHKMKG4QQS7PQOG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K6TVQ27DWXPLHKMKG4QQS7PQOG/action/storage_attestation","attest_author":"https://pith.science/pith/K6TVQ27DWXPLHKMKG4QQS7PQOG/action/author_attestation","sign_citation":"https://pith.science/pith/K6TVQ27DWXPLHKMKG4QQS7PQOG/action/citation_signature","submit_replication":"https://pith.science/pith/K6TVQ27DWXPLHKMKG4QQS7PQOG/action/replication_record"}},"created_at":"2026-07-05T05:13:39.101206+00:00","updated_at":"2026-07-05T05:13:39.101206+00:00"}