{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3ZKYCB7JVECDYYE6J7NHNUSOKV","short_pith_number":"pith:3ZKYCB7J","schema_version":"1.0","canonical_sha256":"de558107e9a9043c609e4fda76d24e5569ea2430f90d6496db8e5629ced01f43","source":{"kind":"arxiv","id":"2606.28152","version":1},"attestation_state":"computed","paper":{"title":"Regularized Reward-Punishment Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Eiji Uchibe, Jiexin Wang","submitted_at":"2026-06-26T14:50:16Z","abstract_excerpt":"We propose KL-Coupled Policy Regularization (KCPR), a policy coordination framework for Reward-Punishment Reinforcement Learning (RPRL). Based on KCPR, we derive KL-Coupled Soft Optimality (KCSO) and develop its deep realization, klDMP. Unlike existing RPRL approaches that optimize reward-seeking and punishment-related policies largely independently, KCPR enables direct interactions between companion policies by treating each as a dynamically learned prior for the other. KCSO yields coupled soft-optimal policies and KL-regularized Bellman operators, allowing reward and punishment information t"},"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":"2606.28152","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T14:50:16Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"687ab549c74bfc0b622eb136ec606ec3c9b138b03260fdfdf194d5e79afc31ea","abstract_canon_sha256":"935a5b94df176b46613079b4df807103ac43633eb4f35faf84553830e1a05506"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:15:07.564174Z","signature_b64":"lAq5NESfb/1SU55yfd/wfAzduC+itoQ9KV3QUNCYmkTYsdRmcus/V7t7TWzBWIK1UEuAfyJ09HYiliFdc7ioCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de558107e9a9043c609e4fda76d24e5569ea2430f90d6496db8e5629ced01f43","last_reissued_at":"2026-06-29T01:15:07.563761Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:15:07.563761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regularized Reward-Punishment Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Eiji Uchibe, Jiexin Wang","submitted_at":"2026-06-26T14:50:16Z","abstract_excerpt":"We propose KL-Coupled Policy Regularization (KCPR), a policy coordination framework for Reward-Punishment Reinforcement Learning (RPRL). Based on KCPR, we derive KL-Coupled Soft Optimality (KCSO) and develop its deep realization, klDMP. Unlike existing RPRL approaches that optimize reward-seeking and punishment-related policies largely independently, KCPR enables direct interactions between companion policies by treating each as a dynamically learned prior for the other. KCSO yields coupled soft-optimal policies and KL-regularized Bellman operators, allowing reward and punishment information t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28152","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/2606.28152/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":"2606.28152","created_at":"2026-06-29T01:15:07.563821+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.28152v1","created_at":"2026-06-29T01:15:07.563821+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28152","created_at":"2026-06-29T01:15:07.563821+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ZKYCB7JVECD","created_at":"2026-06-29T01:15:07.563821+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ZKYCB7JVECDYYE6","created_at":"2026-06-29T01:15:07.563821+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ZKYCB7J","created_at":"2026-06-29T01:15:07.563821+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/3ZKYCB7JVECDYYE6J7NHNUSOKV","json":"https://pith.science/pith/3ZKYCB7JVECDYYE6J7NHNUSOKV.json","graph_json":"https://pith.science/api/pith-number/3ZKYCB7JVECDYYE6J7NHNUSOKV/graph.json","events_json":"https://pith.science/api/pith-number/3ZKYCB7JVECDYYE6J7NHNUSOKV/events.json","paper":"https://pith.science/paper/3ZKYCB7J"},"agent_actions":{"view_html":"https://pith.science/pith/3ZKYCB7JVECDYYE6J7NHNUSOKV","download_json":"https://pith.science/pith/3ZKYCB7JVECDYYE6J7NHNUSOKV.json","view_paper":"https://pith.science/paper/3ZKYCB7J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.28152&json=true","fetch_graph":"https://pith.science/api/pith-number/3ZKYCB7JVECDYYE6J7NHNUSOKV/graph.json","fetch_events":"https://pith.science/api/pith-number/3ZKYCB7JVECDYYE6J7NHNUSOKV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ZKYCB7JVECDYYE6J7NHNUSOKV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ZKYCB7JVECDYYE6J7NHNUSOKV/action/storage_attestation","attest_author":"https://pith.science/pith/3ZKYCB7JVECDYYE6J7NHNUSOKV/action/author_attestation","sign_citation":"https://pith.science/pith/3ZKYCB7JVECDYYE6J7NHNUSOKV/action/citation_signature","submit_replication":"https://pith.science/pith/3ZKYCB7JVECDYYE6J7NHNUSOKV/action/replication_record"}},"created_at":"2026-06-29T01:15:07.563821+00:00","updated_at":"2026-06-29T01:15:07.563821+00:00"}