{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GXMEPQSYR4J6LML27S6KRV6MF2","short_pith_number":"pith:GXMEPQSY","canonical_record":{"source":{"id":"2307.12062","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-22T12:10:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a68b266744760d1cbd36e9b8da688a037a71ae857c78d71803076b0db608cffd","abstract_canon_sha256":"a50f90c3815b7450005e4fc886886f80b76b6db2bba23e95a4effa1696d2ba41"},"schema_version":"1.0"},"canonical_sha256":"35d847c2588f13e5b17afcbca8d7cc2eaf1a07468770735948d5efda6509cd8d","source":{"kind":"arxiv","id":"2307.12062","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.12062","created_at":"2026-07-05T08:11:53Z"},{"alias_kind":"arxiv_version","alias_value":"2307.12062v3","created_at":"2026-07-05T08:11:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12062","created_at":"2026-07-05T08:11:53Z"},{"alias_kind":"pith_short_12","alias_value":"GXMEPQSYR4J6","created_at":"2026-07-05T08:11:53Z"},{"alias_kind":"pith_short_16","alias_value":"GXMEPQSYR4J6LML2","created_at":"2026-07-05T08:11:53Z"},{"alias_kind":"pith_short_8","alias_value":"GXMEPQSY","created_at":"2026-07-05T08:11:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GXMEPQSYR4J6LML27S6KRV6MF2","target":"record","payload":{"canonical_record":{"source":{"id":"2307.12062","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-22T12:10:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a68b266744760d1cbd36e9b8da688a037a71ae857c78d71803076b0db608cffd","abstract_canon_sha256":"a50f90c3815b7450005e4fc886886f80b76b6db2bba23e95a4effa1696d2ba41"},"schema_version":"1.0"},"canonical_sha256":"35d847c2588f13e5b17afcbca8d7cc2eaf1a07468770735948d5efda6509cd8d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:53.492479Z","signature_b64":"5CXoHM/IObZd8MHbfrg5pJd9VSI6ruq/MMsijU/PUHTz3jVPvhTOGZ0rgGQmmretjYn8Me2hTmmxHonHXbVCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35d847c2588f13e5b17afcbca8d7cc2eaf1a07468770735948d5efda6509cd8d","last_reissued_at":"2026-07-05T08:11:53.491927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:53.491927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.12062","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:11:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u3gTaxC9yagEOIC3bXq+g33F8FMbhzetGzOk6cpSnB60gbhQAWkJekv/ElwZIEbJluV6x4fymSxIjVARJ1HEDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:21:09.416946Z"},"content_sha256":"475f5156d9ef10f978d3126c321dd3617f977e9faded02f31fd0e383cf2a2edb","schema_version":"1.0","event_id":"sha256:475f5156d9ef10f978d3126c321dd3617f977e9faded02f31fd0e383cf2a2edb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GXMEPQSYR4J6LML27S6KRV6MF2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Benjamin Eysenbach, Furong Huang, Ruijie Zheng, Stephen McAleer, Tuomas Sandholm, Xiangyu Liu, Yanchao Sun, Yongyuan Liang","submitted_at":"2023-07-22T12:10:04Z","abstract_excerpt":"Deploying reinforcement learning (RL) systems requires robustness to uncertainty and model misspecification, yet prior robust RL methods typically only study noise introduced independently across time. However, practical sources of uncertainty are usually coupled across time. We formally introduce temporally-coupled perturbations, presenting a novel challenge for existing robust RL methods. To tackle this challenge, we propose GRAD, a novel game-theoretic approach that treats the temporally-coupled robust RL problem as a partially observable two-player zero-sum game. By finding an approximate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12062","kind":"arxiv","version":3},"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/2307.12062/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":"2026-07-05T08:11:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jsrjzQtSGQhnkirF/cjkML5107eIeSIUVnQeKQYWIOMvU3s6/j73LQ2DXpu/QD+B7yYfVblqaYOq7x4iJay6AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:21:09.417494Z"},"content_sha256":"cde8fb5c565b13b05d57105016050dd2dc4c18f090427738c9205e81d9bb217c","schema_version":"1.0","event_id":"sha256:cde8fb5c565b13b05d57105016050dd2dc4c18f090427738c9205e81d9bb217c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GXMEPQSYR4J6LML27S6KRV6MF2/bundle.json","state_url":"https://pith.science/pith/GXMEPQSYR4J6LML27S6KRV6MF2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GXMEPQSYR4J6LML27S6KRV6MF2/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":"2026-08-19T15:21:09Z","links":{"resolver":"https://pith.science/pith/GXMEPQSYR4J6LML27S6KRV6MF2","bundle":"https://pith.science/pith/GXMEPQSYR4J6LML27S6KRV6MF2/bundle.json","state":"https://pith.science/pith/GXMEPQSYR4J6LML27S6KRV6MF2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GXMEPQSYR4J6LML27S6KRV6MF2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GXMEPQSYR4J6LML27S6KRV6MF2","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":"a50f90c3815b7450005e4fc886886f80b76b6db2bba23e95a4effa1696d2ba41","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-22T12:10:04Z","title_canon_sha256":"a68b266744760d1cbd36e9b8da688a037a71ae857c78d71803076b0db608cffd"},"schema_version":"1.0","source":{"id":"2307.12062","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.12062","created_at":"2026-07-05T08:11:53Z"},{"alias_kind":"arxiv_version","alias_value":"2307.12062v3","created_at":"2026-07-05T08:11:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12062","created_at":"2026-07-05T08:11:53Z"},{"alias_kind":"pith_short_12","alias_value":"GXMEPQSYR4J6","created_at":"2026-07-05T08:11:53Z"},{"alias_kind":"pith_short_16","alias_value":"GXMEPQSYR4J6LML2","created_at":"2026-07-05T08:11:53Z"},{"alias_kind":"pith_short_8","alias_value":"GXMEPQSY","created_at":"2026-07-05T08:11:53Z"}],"graph_snapshots":[{"event_id":"sha256:cde8fb5c565b13b05d57105016050dd2dc4c18f090427738c9205e81d9bb217c","target":"graph","created_at":"2026-07-05T08:11:53Z","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/2307.12062/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deploying reinforcement learning (RL) systems requires robustness to uncertainty and model misspecification, yet prior robust RL methods typically only study noise introduced independently across time. However, practical sources of uncertainty are usually coupled across time. We formally introduce temporally-coupled perturbations, presenting a novel challenge for existing robust RL methods. To tackle this challenge, we propose GRAD, a novel game-theoretic approach that treats the temporally-coupled robust RL problem as a partially observable two-player zero-sum game. By finding an approximate ","authors_text":"Benjamin Eysenbach, Furong Huang, Ruijie Zheng, Stephen McAleer, Tuomas Sandholm, Xiangyu Liu, Yanchao Sun, Yongyuan Liang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-22T12:10:04Z","title":"Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12062","kind":"arxiv","version":3},"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":"sha256:475f5156d9ef10f978d3126c321dd3617f977e9faded02f31fd0e383cf2a2edb","target":"record","created_at":"2026-07-05T08:11:53Z","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":"a50f90c3815b7450005e4fc886886f80b76b6db2bba23e95a4effa1696d2ba41","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-22T12:10:04Z","title_canon_sha256":"a68b266744760d1cbd36e9b8da688a037a71ae857c78d71803076b0db608cffd"},"schema_version":"1.0","source":{"id":"2307.12062","kind":"arxiv","version":3}},"canonical_sha256":"35d847c2588f13e5b17afcbca8d7cc2eaf1a07468770735948d5efda6509cd8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35d847c2588f13e5b17afcbca8d7cc2eaf1a07468770735948d5efda6509cd8d","first_computed_at":"2026-07-05T08:11:53.491927Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:11:53.491927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5CXoHM/IObZd8MHbfrg5pJd9VSI6ruq/MMsijU/PUHTz3jVPvhTOGZ0rgGQmmretjYn8Me2hTmmxHonHXbVCCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:11:53.492479Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.12062","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:475f5156d9ef10f978d3126c321dd3617f977e9faded02f31fd0e383cf2a2edb","sha256:cde8fb5c565b13b05d57105016050dd2dc4c18f090427738c9205e81d9bb217c"],"state_sha256":"1b6803446aba810ec2f4771108eaf8ed34b5cbb638b0761acdf05c37ddb91e10"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MZ6QDcbb+jAzS0Yxb0DLqKqlB7jTU8mr52rMFsXs1AFUp0XYiFLXvDnk10ywK7vCnGKoKt+J2Bit1sGSKuqZBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T15:21:09.422589Z","bundle_sha256":"c4463fc9187b172b0e39780b42154f051eb89b3120522821c9458dffe16c210e"}}