{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UZONRMVL64VDMAFKKBK7SSFJPL","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":"733587fa37c0b596ccc834b499fa2539c2fe95bbd3e406640998760de57e533f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-08T09:28:11Z","title_canon_sha256":"7ac0da4cfef2f1d785a0c972b8b595bf87774dec337e35184e4114f1bd12df25"},"schema_version":"1.0","source":{"id":"2506.07054","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07054","created_at":"2026-07-05T11:18:00Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07054v1","created_at":"2026-07-05T11:18:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07054","created_at":"2026-07-05T11:18:00Z"},{"alias_kind":"pith_short_12","alias_value":"UZONRMVL64VD","created_at":"2026-07-05T11:18:00Z"},{"alias_kind":"pith_short_16","alias_value":"UZONRMVL64VDMAFK","created_at":"2026-07-05T11:18:00Z"},{"alias_kind":"pith_short_8","alias_value":"UZONRMVL","created_at":"2026-07-05T11:18:00Z"}],"graph_snapshots":[{"event_id":"sha256:f8c0b5ea3bf8eff7ea0516613377aa554313a7dc032be635197fb6f6b3959ab2","target":"graph","created_at":"2026-07-05T11:18:00Z","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/2506.07054/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Classical policy gradient (PG) methods in reinforcement learning frequently converge to suboptimal local optima, a challenge exacerbated in large or complex environments. This work investigates Policy Gradient with Tree Search (PGTS), an approach that integrates an $m$-step lookahead mechanism to enhance policy optimization. We provide theoretical analysis demonstrating that increasing the tree search depth $m$-monotonically reduces the set of undesirable stationary points and, consequently, improves the worst-case performance of any resulting stationary policy. Critically, our analysis accomm","authors_text":"Giorgia Ramponi, Kfir Yehuda Levy, Navdeep Kumar, Shie Mannor, Uri Gadot, Uri Koren","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-08T09:28:11Z","title":"Policy Gradient with Tree Search: Avoiding Local Optimas through Lookahead"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07054","kind":"arxiv","version":1},"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:c0f6a78771bdb20504a9b506aa036f9758e5b51b40fba82e717271e7018fd50f","target":"record","created_at":"2026-07-05T11:18:00Z","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":"733587fa37c0b596ccc834b499fa2539c2fe95bbd3e406640998760de57e533f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-08T09:28:11Z","title_canon_sha256":"7ac0da4cfef2f1d785a0c972b8b595bf87774dec337e35184e4114f1bd12df25"},"schema_version":"1.0","source":{"id":"2506.07054","kind":"arxiv","version":1}},"canonical_sha256":"a65cd8b2abf72a3600aa5055f948a97ae4f071a466816f1281ce3b0786a4c4ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a65cd8b2abf72a3600aa5055f948a97ae4f071a466816f1281ce3b0786a4c4ed","first_computed_at":"2026-07-05T11:18:00.454341Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:00.454341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wnsAaAX9sSXo5qWHuQ3EmUQP5+iGIPgsKiTkLfxCLY4WZ67tWIcnS58JpbohtFagEhHGb7JNkj7wqZEbwYe+DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:00.454891Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07054","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0f6a78771bdb20504a9b506aa036f9758e5b51b40fba82e717271e7018fd50f","sha256:f8c0b5ea3bf8eff7ea0516613377aa554313a7dc032be635197fb6f6b3959ab2"],"state_sha256":"687ad5313da882b054e0a4d91f3e312fc5cccb409bdb8de5157bb9624573ca92"}