{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LMJD7D2SRBOCVAJDC5EBNQQY3J","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":"ee130795c7d0f41dbb4f60cdf186f4dca788d5990675e6168e14533e49316d1f","cross_cats_sorted":["cs.SY","eess.SY","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-17T23:37:21Z","title_canon_sha256":"386a001918b308daa44279ddbabb46f0ab516d6f82a528cac8a27a3d17b1f009"},"schema_version":"1.0","source":{"id":"2501.10605","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.10605","created_at":"2026-07-05T10:26:12Z"},{"alias_kind":"arxiv_version","alias_value":"2501.10605v2","created_at":"2026-07-05T10:26:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10605","created_at":"2026-07-05T10:26:12Z"},{"alias_kind":"pith_short_12","alias_value":"LMJD7D2SRBOC","created_at":"2026-07-05T10:26:12Z"},{"alias_kind":"pith_short_16","alias_value":"LMJD7D2SRBOCVAJD","created_at":"2026-07-05T10:26:12Z"},{"alias_kind":"pith_short_8","alias_value":"LMJD7D2S","created_at":"2026-07-05T10:26:12Z"}],"graph_snapshots":[{"event_id":"sha256:82e270d6a0301f06315500063f3292245c59a0cfa2604e747a5ecded2d7fa91d","target":"graph","created_at":"2026-07-05T10:26:12Z","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/2501.10605/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Wasserstein Adaptive Value Estimation for Actor-Critic (WAVE), an approach to enhance stability in deep reinforcement learning through adaptive Wasserstein regularization. Our method addresses the inherent instability of actor-critic algorithms by incorporating an adaptively weighted Wasserstein regularization term into the critic's loss function. We prove that WAVE achieves $\\mathcal{O}\\left(\\frac{1}{k}\\right)$ convergence rate for the critic's mean squared error and provide theoretical guarantees for stability through Wasserstein-based regularization. Using the Sinkhorn approximat","authors_text":"Ali Baheri, Chirayu Salgarkar, Zahra Shahrooei","cross_cats":["cs.SY","eess.SY","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-17T23:37:21Z","title":"Wasserstein Adaptive Value Estimation for Actor-Critic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10605","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":"sha256:04e0311a441a5900593f8523287c9e03f053e59e9cea7f633fcb485e50e3abf6","target":"record","created_at":"2026-07-05T10:26:12Z","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":"ee130795c7d0f41dbb4f60cdf186f4dca788d5990675e6168e14533e49316d1f","cross_cats_sorted":["cs.SY","eess.SY","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-17T23:37:21Z","title_canon_sha256":"386a001918b308daa44279ddbabb46f0ab516d6f82a528cac8a27a3d17b1f009"},"schema_version":"1.0","source":{"id":"2501.10605","kind":"arxiv","version":2}},"canonical_sha256":"5b123f8f52885c2a8123174816c218da6046a72e38da9867de854587e408ed32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b123f8f52885c2a8123174816c218da6046a72e38da9867de854587e408ed32","first_computed_at":"2026-07-05T10:26:12.539741Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:26:12.539741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O6GKSpAVJhnDRgx5rglzwWxYV+hoCZ5RUCT7TRIVxFQwhvSQ7IQlMI3HpnNNX6wvN0DSjdOhEEIQhCD8mxuiCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:26:12.540221Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.10605","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04e0311a441a5900593f8523287c9e03f053e59e9cea7f633fcb485e50e3abf6","sha256:82e270d6a0301f06315500063f3292245c59a0cfa2604e747a5ecded2d7fa91d"],"state_sha256":"738ead79bc54b98c03c639ebac001218e69156cfa8b3ed599dedbd8ddac1e671"}