{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SODMVGEULLXYL6NLYJ7RMP6TRJ","short_pith_number":"pith:SODMVGEU","schema_version":"1.0","canonical_sha256":"9386ca98945aef85f9abc27f163fd38a7de49b2760ff4df8555cbf1d8bb5fcc5","source":{"kind":"arxiv","id":"2602.10894","version":2},"attestation_state":"computed","paper":{"title":"Revisiting Regularized Policy Optimization for Stable and Efficient Reinforcement Learning in Two-Player Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kazuki Ota, Motoki Omura, Takayuki Osa, Tatsuya Harada","submitted_at":"2026-02-11T14:25:38Z","abstract_excerpt":"Two-player games such as board games have long been used as traditional benchmarks for reinforcement learning. This work revisits a policy optimization method with reverse Kullback-Leibler regularization and entropy regularization and analyzes this combination in two-player zero-sum settings from theoretical and empirical perspectives. From a theoretical perspective, we investigate the stability of the policy update rule in two theoretical settings: game-theoretic normal-form games and finite-length games. We provide novel convergence guarantees and verify our theoretical results through numer"},"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":"2602.10894","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-11T14:25:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0e99f88961f75e13dee7138345ee3b9d9d4c5cac9a8989e744683f2f5f4f5630","abstract_canon_sha256":"8bfefb7991d44f485d672f5eafa151aa34d575868c15fcfc9c503bfe293539a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:57.299159Z","signature_b64":"0nyoC25UBemJxXap6fjA2dtNzAw4LDpbC28tod3kFVgb5Y8Ms+Q53HU7pwLzG/sZjxo9ij1iSc/xtL+6qKjFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9386ca98945aef85f9abc27f163fd38a7de49b2760ff4df8555cbf1d8bb5fcc5","last_reissued_at":"2026-05-22T01:03:57.298517Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:57.298517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Regularized Policy Optimization for Stable and Efficient Reinforcement Learning in Two-Player Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kazuki Ota, Motoki Omura, Takayuki Osa, Tatsuya Harada","submitted_at":"2026-02-11T14:25:38Z","abstract_excerpt":"Two-player games such as board games have long been used as traditional benchmarks for reinforcement learning. This work revisits a policy optimization method with reverse Kullback-Leibler regularization and entropy regularization and analyzes this combination in two-player zero-sum settings from theoretical and empirical perspectives. From a theoretical perspective, we investigate the stability of the policy update rule in two theoretical settings: game-theoretic normal-form games and finite-length games. We provide novel convergence guarantees and verify our theoretical results through numer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.10894","kind":"arxiv","version":2},"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/2602.10894/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":"2602.10894","created_at":"2026-05-22T01:03:57.298607+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.10894v2","created_at":"2026-05-22T01:03:57.298607+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.10894","created_at":"2026-05-22T01:03:57.298607+00:00"},{"alias_kind":"pith_short_12","alias_value":"SODMVGEULLXY","created_at":"2026-05-22T01:03:57.298607+00:00"},{"alias_kind":"pith_short_16","alias_value":"SODMVGEULLXYL6NL","created_at":"2026-05-22T01:03:57.298607+00:00"},{"alias_kind":"pith_short_8","alias_value":"SODMVGEU","created_at":"2026-05-22T01:03:57.298607+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/SODMVGEULLXYL6NLYJ7RMP6TRJ","json":"https://pith.science/pith/SODMVGEULLXYL6NLYJ7RMP6TRJ.json","graph_json":"https://pith.science/api/pith-number/SODMVGEULLXYL6NLYJ7RMP6TRJ/graph.json","events_json":"https://pith.science/api/pith-number/SODMVGEULLXYL6NLYJ7RMP6TRJ/events.json","paper":"https://pith.science/paper/SODMVGEU"},"agent_actions":{"view_html":"https://pith.science/pith/SODMVGEULLXYL6NLYJ7RMP6TRJ","download_json":"https://pith.science/pith/SODMVGEULLXYL6NLYJ7RMP6TRJ.json","view_paper":"https://pith.science/paper/SODMVGEU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.10894&json=true","fetch_graph":"https://pith.science/api/pith-number/SODMVGEULLXYL6NLYJ7RMP6TRJ/graph.json","fetch_events":"https://pith.science/api/pith-number/SODMVGEULLXYL6NLYJ7RMP6TRJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SODMVGEULLXYL6NLYJ7RMP6TRJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SODMVGEULLXYL6NLYJ7RMP6TRJ/action/storage_attestation","attest_author":"https://pith.science/pith/SODMVGEULLXYL6NLYJ7RMP6TRJ/action/author_attestation","sign_citation":"https://pith.science/pith/SODMVGEULLXYL6NLYJ7RMP6TRJ/action/citation_signature","submit_replication":"https://pith.science/pith/SODMVGEULLXYL6NLYJ7RMP6TRJ/action/replication_record"}},"created_at":"2026-05-22T01:03:57.298607+00:00","updated_at":"2026-05-22T01:03:57.298607+00:00"}