{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:A4I7PQJX2VCEWCUBEE5GA4PRGN","short_pith_number":"pith:A4I7PQJX","canonical_record":{"source":{"id":"2406.11774","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T17:32:25Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"be2d1e5eb1c04cd41fea4557e4ad2a4c011f8beb1998f9d2713eecbd7875b408","abstract_canon_sha256":"9f5e9d08afab94047dacf9ea3ed3185519794fc077a6d474fb8d18a1b0fd1cff"},"schema_version":"1.0"},"canonical_sha256":"0711f7c137d5444b0a81213a6071f1336e8179536c9fb1d6f7184467fab9fccb","source":{"kind":"arxiv","id":"2406.11774","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11774","created_at":"2026-07-05T09:06:06Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11774v2","created_at":"2026-07-05T09:06:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11774","created_at":"2026-07-05T09:06:06Z"},{"alias_kind":"pith_short_12","alias_value":"A4I7PQJX2VCE","created_at":"2026-07-05T09:06:06Z"},{"alias_kind":"pith_short_16","alias_value":"A4I7PQJX2VCEWCUB","created_at":"2026-07-05T09:06:06Z"},{"alias_kind":"pith_short_8","alias_value":"A4I7PQJX","created_at":"2026-07-05T09:06:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:A4I7PQJX2VCEWCUBEE5GA4PRGN","target":"record","payload":{"canonical_record":{"source":{"id":"2406.11774","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T17:32:25Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"be2d1e5eb1c04cd41fea4557e4ad2a4c011f8beb1998f9d2713eecbd7875b408","abstract_canon_sha256":"9f5e9d08afab94047dacf9ea3ed3185519794fc077a6d474fb8d18a1b0fd1cff"},"schema_version":"1.0"},"canonical_sha256":"0711f7c137d5444b0a81213a6071f1336e8179536c9fb1d6f7184467fab9fccb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:06.295848Z","signature_b64":"M1fFWmza9+r65kL6GST/g43Melc8xbsdWUmAlE1u9kd+FFv1IRCAhqpURPy/67S1YXUFXVx4sCDPqgMQPESTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0711f7c137d5444b0a81213a6071f1336e8179536c9fb1d6f7184467fab9fccb","last_reissued_at":"2026-07-05T09:06:06.295449Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:06.295449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.11774","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":"2026-07-05T09:06:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KACMsSKoFAGZXwx7oxzTeylhHyRIvVO8RfGfBvVuSuWsd0+JGYJB0opFuOxApK65vNP/8WnPJWgeiwT8XJmoAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T14:44:34.282644Z"},"content_sha256":"f08255d503dfe160f6f57a40c7f34352158cd530733d2667330bb1640ba58c25","schema_version":"1.0","event_id":"sha256:f08255d503dfe160f6f57a40c7f34352158cd530733d2667330bb1640ba58c25"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:A4I7PQJX2VCEWCUBEE5GA4PRGN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimal Transport-Assisted Risk-Sensitive Q-Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Ali Baheri, Zahra Shahrooei","submitted_at":"2024-06-17T17:32:25Z","abstract_excerpt":"The primary goal of reinforcement learning is to develop decision-making policies that prioritize optimal performance without considering risk or safety. In contrast, safe reinforcement learning aims to mitigate or avoid unsafe states. This paper presents a risk-sensitive Q-learning algorithm that leverages optimal transport theory to enhance the agent safety. By integrating optimal transport into the Q-learning framework, our approach seeks to optimize the policy's expected return while minimizing the Wasserstein distance between the policy's stationary distribution and a predefined risk dist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11774","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/2406.11774/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":"2026-07-05T09:06:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OopHG70T++nog+YQqbQoBKGV5W2kNopdJSZ9PSwdLSmxUrie2Et7xEGRaajFV1g5JYKD7Y+7Rn3ldBORyagSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T14:44:34.283177Z"},"content_sha256":"4cbe3fad3a32b91286bee651bd574594e02b8289261f7c3cd4cc356a00fc23e9","schema_version":"1.0","event_id":"sha256:4cbe3fad3a32b91286bee651bd574594e02b8289261f7c3cd4cc356a00fc23e9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A4I7PQJX2VCEWCUBEE5GA4PRGN/bundle.json","state_url":"https://pith.science/pith/A4I7PQJX2VCEWCUBEE5GA4PRGN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A4I7PQJX2VCEWCUBEE5GA4PRGN/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":"2026-08-11T14:44:34Z","links":{"resolver":"https://pith.science/pith/A4I7PQJX2VCEWCUBEE5GA4PRGN","bundle":"https://pith.science/pith/A4I7PQJX2VCEWCUBEE5GA4PRGN/bundle.json","state":"https://pith.science/pith/A4I7PQJX2VCEWCUBEE5GA4PRGN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A4I7PQJX2VCEWCUBEE5GA4PRGN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:A4I7PQJX2VCEWCUBEE5GA4PRGN","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":"9f5e9d08afab94047dacf9ea3ed3185519794fc077a6d474fb8d18a1b0fd1cff","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T17:32:25Z","title_canon_sha256":"be2d1e5eb1c04cd41fea4557e4ad2a4c011f8beb1998f9d2713eecbd7875b408"},"schema_version":"1.0","source":{"id":"2406.11774","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11774","created_at":"2026-07-05T09:06:06Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11774v2","created_at":"2026-07-05T09:06:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11774","created_at":"2026-07-05T09:06:06Z"},{"alias_kind":"pith_short_12","alias_value":"A4I7PQJX2VCE","created_at":"2026-07-05T09:06:06Z"},{"alias_kind":"pith_short_16","alias_value":"A4I7PQJX2VCEWCUB","created_at":"2026-07-05T09:06:06Z"},{"alias_kind":"pith_short_8","alias_value":"A4I7PQJX","created_at":"2026-07-05T09:06:06Z"}],"graph_snapshots":[{"event_id":"sha256:4cbe3fad3a32b91286bee651bd574594e02b8289261f7c3cd4cc356a00fc23e9","target":"graph","created_at":"2026-07-05T09:06:06Z","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/2406.11774/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The primary goal of reinforcement learning is to develop decision-making policies that prioritize optimal performance without considering risk or safety. In contrast, safe reinforcement learning aims to mitigate or avoid unsafe states. This paper presents a risk-sensitive Q-learning algorithm that leverages optimal transport theory to enhance the agent safety. By integrating optimal transport into the Q-learning framework, our approach seeks to optimize the policy's expected return while minimizing the Wasserstein distance between the policy's stationary distribution and a predefined risk dist","authors_text":"Ali Baheri, Zahra Shahrooei","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T17:32:25Z","title":"Optimal Transport-Assisted Risk-Sensitive Q-Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11774","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:f08255d503dfe160f6f57a40c7f34352158cd530733d2667330bb1640ba58c25","target":"record","created_at":"2026-07-05T09:06:06Z","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":"9f5e9d08afab94047dacf9ea3ed3185519794fc077a6d474fb8d18a1b0fd1cff","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T17:32:25Z","title_canon_sha256":"be2d1e5eb1c04cd41fea4557e4ad2a4c011f8beb1998f9d2713eecbd7875b408"},"schema_version":"1.0","source":{"id":"2406.11774","kind":"arxiv","version":2}},"canonical_sha256":"0711f7c137d5444b0a81213a6071f1336e8179536c9fb1d6f7184467fab9fccb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0711f7c137d5444b0a81213a6071f1336e8179536c9fb1d6f7184467fab9fccb","first_computed_at":"2026-07-05T09:06:06.295449Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:06:06.295449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M1fFWmza9+r65kL6GST/g43Melc8xbsdWUmAlE1u9kd+FFv1IRCAhqpURPy/67S1YXUFXVx4sCDPqgMQPESTBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:06:06.295848Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11774","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f08255d503dfe160f6f57a40c7f34352158cd530733d2667330bb1640ba58c25","sha256:4cbe3fad3a32b91286bee651bd574594e02b8289261f7c3cd4cc356a00fc23e9"],"state_sha256":"522f4aab51c9add29cb4d900a160e80bf56ecb265d8046ac99a6e138864fb483"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rFu+VpDFp08qWX6vQ0JjIwPaQsTTEx8TPAti5UFdvQcEbI5WipgQtpM0VXK5smLiY8WkDr02zO7cZeo0AY14Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T14:44:34.286906Z","bundle_sha256":"b73a893b09d57bdca31ae6c54b87e56adf3b0dd85b1b78d8658cf40200256e33"}}