{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NTG7XVFYHXT3TMQ3DNV4NM432X","short_pith_number":"pith:NTG7XVFY","schema_version":"1.0","canonical_sha256":"6ccdfbd4b83de7b9b21b1b6bc6b39bd5f8e705f23ef111a7bbb17b34b65b96fb","source":{"kind":"arxiv","id":"2309.06239","version":1},"attestation_state":"computed","paper":{"title":"Risk-Aware Reinforcement Learning through Optimal Transport Theory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Ali Baheri","submitted_at":"2023-09-12T13:55:01Z","abstract_excerpt":"In the dynamic and uncertain environments where reinforcement learning (RL) operates, risk management becomes a crucial factor in ensuring reliable decision-making. Traditional RL approaches, while effective in reward optimization, often overlook the landscape of potential risks. In response, this paper pioneers the integration of Optimal Transport (OT) theory with RL to create a risk-aware framework. Our approach modifies the objective function, ensuring that the resulting policy not only maximizes expected rewards but also respects risk constraints dictated by OT distances between state visi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2309.06239","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-12T13:55:01Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"289c0b73498d7d0b5c7ae99c7bb9f0eb5dedd250004a3182de1953fc235e4616","abstract_canon_sha256":"197f968c5de34da6aa7f70833e8101f3c1853119e547e60eff293b839f616782"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:05.369626Z","signature_b64":"8dXH8n8XgjyUfVg+biNRbY/IHB13+PzueOrE98c12JTDCZscc4heux9CCRfo3HJE+1M0KrFvS1s4JI6gY0GfCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ccdfbd4b83de7b9b21b1b6bc6b39bd5f8e705f23ef111a7bbb17b34b65b96fb","last_reissued_at":"2026-07-05T06:50:05.369062Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:05.369062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Risk-Aware Reinforcement Learning through Optimal Transport Theory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Ali Baheri","submitted_at":"2023-09-12T13:55:01Z","abstract_excerpt":"In the dynamic and uncertain environments where reinforcement learning (RL) operates, risk management becomes a crucial factor in ensuring reliable decision-making. Traditional RL approaches, while effective in reward optimization, often overlook the landscape of potential risks. In response, this paper pioneers the integration of Optimal Transport (OT) theory with RL to create a risk-aware framework. Our approach modifies the objective function, ensuring that the resulting policy not only maximizes expected rewards but also respects risk constraints dictated by OT distances between state visi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.06239","kind":"arxiv","version":1},"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/2309.06239/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2309.06239","created_at":"2026-07-05T06:50:05.369126+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.06239v1","created_at":"2026-07-05T06:50:05.369126+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.06239","created_at":"2026-07-05T06:50:05.369126+00:00"},{"alias_kind":"pith_short_12","alias_value":"NTG7XVFYHXT3","created_at":"2026-07-05T06:50:05.369126+00:00"},{"alias_kind":"pith_short_16","alias_value":"NTG7XVFYHXT3TMQ3","created_at":"2026-07-05T06:50:05.369126+00:00"},{"alias_kind":"pith_short_8","alias_value":"NTG7XVFY","created_at":"2026-07-05T06:50:05.369126+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.14521","citing_title":"Geometry-Aware Decentralized Sinkhorn for Wasserstein Barycenters","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NTG7XVFYHXT3TMQ3DNV4NM432X","json":"https://pith.science/pith/NTG7XVFYHXT3TMQ3DNV4NM432X.json","graph_json":"https://pith.science/api/pith-number/NTG7XVFYHXT3TMQ3DNV4NM432X/graph.json","events_json":"https://pith.science/api/pith-number/NTG7XVFYHXT3TMQ3DNV4NM432X/events.json","paper":"https://pith.science/paper/NTG7XVFY"},"agent_actions":{"view_html":"https://pith.science/pith/NTG7XVFYHXT3TMQ3DNV4NM432X","download_json":"https://pith.science/pith/NTG7XVFYHXT3TMQ3DNV4NM432X.json","view_paper":"https://pith.science/paper/NTG7XVFY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.06239&json=true","fetch_graph":"https://pith.science/api/pith-number/NTG7XVFYHXT3TMQ3DNV4NM432X/graph.json","fetch_events":"https://pith.science/api/pith-number/NTG7XVFYHXT3TMQ3DNV4NM432X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NTG7XVFYHXT3TMQ3DNV4NM432X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NTG7XVFYHXT3TMQ3DNV4NM432X/action/storage_attestation","attest_author":"https://pith.science/pith/NTG7XVFYHXT3TMQ3DNV4NM432X/action/author_attestation","sign_citation":"https://pith.science/pith/NTG7XVFYHXT3TMQ3DNV4NM432X/action/citation_signature","submit_replication":"https://pith.science/pith/NTG7XVFYHXT3TMQ3DNV4NM432X/action/replication_record"}},"created_at":"2026-07-05T06:50:05.369126+00:00","updated_at":"2026-07-05T06:50:05.369126+00:00"}