{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SODMVGEULLXYL6NLYJ7RMP6TRJ","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":"8bfefb7991d44f485d672f5eafa151aa34d575868c15fcfc9c503bfe293539a1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-11T14:25:38Z","title_canon_sha256":"0e99f88961f75e13dee7138345ee3b9d9d4c5cac9a8989e744683f2f5f4f5630"},"schema_version":"1.0","source":{"id":"2602.10894","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.10894","created_at":"2026-05-22T01:03:57Z"},{"alias_kind":"arxiv_version","alias_value":"2602.10894v2","created_at":"2026-05-22T01:03:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.10894","created_at":"2026-05-22T01:03:57Z"},{"alias_kind":"pith_short_12","alias_value":"SODMVGEULLXY","created_at":"2026-05-22T01:03:57Z"},{"alias_kind":"pith_short_16","alias_value":"SODMVGEULLXYL6NL","created_at":"2026-05-22T01:03:57Z"},{"alias_kind":"pith_short_8","alias_value":"SODMVGEU","created_at":"2026-05-22T01:03:57Z"}],"graph_snapshots":[{"event_id":"sha256:1b737012ae86f670c7c32fea7e53dd21a98ce8e130e4dac54ad191e76c973c31","target":"graph","created_at":"2026-05-22T01:03:57Z","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/2602.10894/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Kazuki Ota, Motoki Omura, Takayuki Osa, Tatsuya Harada","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-11T14:25:38Z","title":"Revisiting Regularized Policy Optimization for Stable and Efficient Reinforcement Learning in Two-Player Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.10894","kind":"arxiv","version":2},"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":"sha256:8c27ed14efd469404fdfbafffd9440276b126f1ffa9eacd4e8eb1bab8be9f61c","target":"record","created_at":"2026-05-22T01:03:57Z","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":"8bfefb7991d44f485d672f5eafa151aa34d575868c15fcfc9c503bfe293539a1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-11T14:25:38Z","title_canon_sha256":"0e99f88961f75e13dee7138345ee3b9d9d4c5cac9a8989e744683f2f5f4f5630"},"schema_version":"1.0","source":{"id":"2602.10894","kind":"arxiv","version":2}},"canonical_sha256":"9386ca98945aef85f9abc27f163fd38a7de49b2760ff4df8555cbf1d8bb5fcc5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9386ca98945aef85f9abc27f163fd38a7de49b2760ff4df8555cbf1d8bb5fcc5","first_computed_at":"2026-05-22T01:03:57.298517Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:57.298517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0nyoC25UBemJxXap6fjA2dtNzAw4LDpbC28tod3kFVgb5Y8Ms+Q53HU7pwLzG/sZjxo9ij1iSc/xtL+6qKjFDw==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:57.299159Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.10894","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c27ed14efd469404fdfbafffd9440276b126f1ffa9eacd4e8eb1bab8be9f61c","sha256:1b737012ae86f670c7c32fea7e53dd21a98ce8e130e4dac54ad191e76c973c31"],"state_sha256":"4aed6d9075e9ad64c4629729e660deb14f0f88abfb2325069b45f85c0146ec17"}