{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PGR3FZTGRBYFPMVZKNMGKUO67K","short_pith_number":"pith:PGR3FZTG","canonical_record":{"source":{"id":"2506.00801","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"math.OC","submitted_at":"2025-06-01T03:04:37Z","cross_cats_sorted":[],"title_canon_sha256":"cf2ba66592dda4a14f92d09279af3fbde197ab1f9fecfc34e3a7418a9906e917","abstract_canon_sha256":"d7e476b5081889dd7047904c7acb22ca70d38ff49a6a5b015fe49e1fa4829115"},"schema_version":"1.0"},"canonical_sha256":"79a3b2e666887057b2b953586551defa9e0751ac0a3975e706260b9a9347ef34","source":{"kind":"arxiv","id":"2506.00801","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00801","created_at":"2026-07-05T11:30:23Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00801v2","created_at":"2026-07-05T11:30:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00801","created_at":"2026-07-05T11:30:23Z"},{"alias_kind":"pith_short_12","alias_value":"PGR3FZTGRBYF","created_at":"2026-07-05T11:30:23Z"},{"alias_kind":"pith_short_16","alias_value":"PGR3FZTGRBYFPMVZ","created_at":"2026-07-05T11:30:23Z"},{"alias_kind":"pith_short_8","alias_value":"PGR3FZTG","created_at":"2026-07-05T11:30:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PGR3FZTGRBYFPMVZKNMGKUO67K","target":"record","payload":{"canonical_record":{"source":{"id":"2506.00801","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"math.OC","submitted_at":"2025-06-01T03:04:37Z","cross_cats_sorted":[],"title_canon_sha256":"cf2ba66592dda4a14f92d09279af3fbde197ab1f9fecfc34e3a7418a9906e917","abstract_canon_sha256":"d7e476b5081889dd7047904c7acb22ca70d38ff49a6a5b015fe49e1fa4829115"},"schema_version":"1.0"},"canonical_sha256":"79a3b2e666887057b2b953586551defa9e0751ac0a3975e706260b9a9347ef34","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:23.294120Z","signature_b64":"ct7xoN6TGZCKtXbIpSIDhw4iWKCMebRhTfuMr0gmmQRByKjoWbJQ+hGA2Q3M1pBD/ePintjcUGL6UZrVbi9DAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79a3b2e666887057b2b953586551defa9e0751ac0a3975e706260b9a9347ef34","last_reissued_at":"2026-07-05T11:30:23.293624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:23.293624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.00801","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:30:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OBgBLgv3v4czmiEtMCvUGJCUZMl9c6EP1TLO+Hw6A97sTxeJ4bTDwLGKHaM3S1Zf3yjp5/8Xa8X10OIj9HrRCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T05:27:02.714904Z"},"content_sha256":"11ac53313c8488369185cdb77d1f2ceaa02fa1c9f1a8ae153e6fd6bd20e9f846","schema_version":"1.0","event_id":"sha256:11ac53313c8488369185cdb77d1f2ceaa02fa1c9f1a8ae153e6fd6bd20e9f846"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PGR3FZTGRBYFPMVZKNMGKUO67K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adversarial Reinforcement Learning: A Duality-Based Approach To Solving Optimal Control Problems","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Mengzhou Liu, Nan Chen, Nanyi Zhang, Xiaoyan Wang","submitted_at":"2025-06-01T03:04:37Z","abstract_excerpt":"We propose an adversarial deep reinforcement learning (ADRL) algorithm for high-dimensional stochastic control problems. Inspired by the information relaxation duality, ADRL reformulates the control problem as a min-max optimization between policies and adversarial penalties, enforcing non-anticipativity while preserving optimality. Numerical experiments demonstrate ADRL's superior performance to yield tight dual gaps. Our results highlight the potential of ADRL as a robust computational framework for high-dimensional stochastic control in simulation-based optimization contexts."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00801","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/2506.00801/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:30:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WWvvnFN1qhjborz44L63nyuQrovR1rgwfbhL1x9N/txzVRk94YHQIowHPyxE02UkzZDyLKbRZ0xbjOgKLMbdDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T05:27:02.715401Z"},"content_sha256":"952bebeb7f95e12f5c7548d0322089131cf3c047375b6d47ec78de004d8ae05d","schema_version":"1.0","event_id":"sha256:952bebeb7f95e12f5c7548d0322089131cf3c047375b6d47ec78de004d8ae05d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PGR3FZTGRBYFPMVZKNMGKUO67K/bundle.json","state_url":"https://pith.science/pith/PGR3FZTGRBYFPMVZKNMGKUO67K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PGR3FZTGRBYFPMVZKNMGKUO67K/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-21T05:27:02Z","links":{"resolver":"https://pith.science/pith/PGR3FZTGRBYFPMVZKNMGKUO67K","bundle":"https://pith.science/pith/PGR3FZTGRBYFPMVZKNMGKUO67K/bundle.json","state":"https://pith.science/pith/PGR3FZTGRBYFPMVZKNMGKUO67K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PGR3FZTGRBYFPMVZKNMGKUO67K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PGR3FZTGRBYFPMVZKNMGKUO67K","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":"d7e476b5081889dd7047904c7acb22ca70d38ff49a6a5b015fe49e1fa4829115","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"math.OC","submitted_at":"2025-06-01T03:04:37Z","title_canon_sha256":"cf2ba66592dda4a14f92d09279af3fbde197ab1f9fecfc34e3a7418a9906e917"},"schema_version":"1.0","source":{"id":"2506.00801","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00801","created_at":"2026-07-05T11:30:23Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00801v2","created_at":"2026-07-05T11:30:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00801","created_at":"2026-07-05T11:30:23Z"},{"alias_kind":"pith_short_12","alias_value":"PGR3FZTGRBYF","created_at":"2026-07-05T11:30:23Z"},{"alias_kind":"pith_short_16","alias_value":"PGR3FZTGRBYFPMVZ","created_at":"2026-07-05T11:30:23Z"},{"alias_kind":"pith_short_8","alias_value":"PGR3FZTG","created_at":"2026-07-05T11:30:23Z"}],"graph_snapshots":[{"event_id":"sha256:952bebeb7f95e12f5c7548d0322089131cf3c047375b6d47ec78de004d8ae05d","target":"graph","created_at":"2026-07-05T11:30:23Z","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/2506.00801/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose an adversarial deep reinforcement learning (ADRL) algorithm for high-dimensional stochastic control problems. Inspired by the information relaxation duality, ADRL reformulates the control problem as a min-max optimization between policies and adversarial penalties, enforcing non-anticipativity while preserving optimality. Numerical experiments demonstrate ADRL's superior performance to yield tight dual gaps. Our results highlight the potential of ADRL as a robust computational framework for high-dimensional stochastic control in simulation-based optimization contexts.","authors_text":"Mengzhou Liu, Nan Chen, Nanyi Zhang, Xiaoyan Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"math.OC","submitted_at":"2025-06-01T03:04:37Z","title":"Adversarial Reinforcement Learning: A Duality-Based Approach To Solving Optimal Control Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00801","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":"sha256:11ac53313c8488369185cdb77d1f2ceaa02fa1c9f1a8ae153e6fd6bd20e9f846","target":"record","created_at":"2026-07-05T11:30:23Z","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":"d7e476b5081889dd7047904c7acb22ca70d38ff49a6a5b015fe49e1fa4829115","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"math.OC","submitted_at":"2025-06-01T03:04:37Z","title_canon_sha256":"cf2ba66592dda4a14f92d09279af3fbde197ab1f9fecfc34e3a7418a9906e917"},"schema_version":"1.0","source":{"id":"2506.00801","kind":"arxiv","version":2}},"canonical_sha256":"79a3b2e666887057b2b953586551defa9e0751ac0a3975e706260b9a9347ef34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79a3b2e666887057b2b953586551defa9e0751ac0a3975e706260b9a9347ef34","first_computed_at":"2026-07-05T11:30:23.293624Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:23.293624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ct7xoN6TGZCKtXbIpSIDhw4iWKCMebRhTfuMr0gmmQRByKjoWbJQ+hGA2Q3M1pBD/ePintjcUGL6UZrVbi9DAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:23.294120Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00801","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11ac53313c8488369185cdb77d1f2ceaa02fa1c9f1a8ae153e6fd6bd20e9f846","sha256:952bebeb7f95e12f5c7548d0322089131cf3c047375b6d47ec78de004d8ae05d"],"state_sha256":"a2aefaada9c2e2e7a6563234c9eefbd4687d53c2d319431d4e70460131c160d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jcul4rS5bcVUh9Fl8jl8LBItkUk393IIRLrLAaUm3TtOxx1tTk+3Qf8nhkm2SNPqj3cDqBb2z+z4Xv8PDPpSCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T05:27:02.719419Z","bundle_sha256":"2b91afdad54697d8024adbe870804dc434893d6181d29e67f830372aac1a6d90"}}