{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FPODNIRO32K2P5J6N35ZINTM3S","short_pith_number":"pith:FPODNIRO","schema_version":"1.0","canonical_sha256":"2bdc36a22ede95a7f53e6efb94366cdcb279bbedb9cdb1c2abd22e52892b468e","source":{"kind":"arxiv","id":"2302.05209","version":3},"attestation_state":"computed","paper":{"title":"A Survey on Causal Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Fuchun Sun, Libo Huang, Ruichu Cai, Yan Zeng, Zhifeng Hao","submitted_at":"2023-02-10T12:25:08Z","abstract_excerpt":"While Reinforcement Learning (RL) achieves tremendous success in sequential decision-making problems of many domains, it still faces key challenges of data inefficiency and the lack of interpretability. Interestingly, many researchers have leveraged insights from the causality literature recently, bringing forth flourishing works to unify the merits of causality and address well the challenges from RL. As such, it is of great necessity and significance to collate these Causal Reinforcement Learning (CRL) works, offer a review of CRL methods, and investigate the potential functionality from cau"},"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":"2302.05209","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-02-10T12:25:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cb31f5dba8a6d71c6706da0fb8cd6ecf29aebf17c7b1ec08471c2be4106e4023","abstract_canon_sha256":"0859066889d57f7d44e60cfc22b6bcc360e8b6de51c0772b0cc9c8c21454d3fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:15.987279Z","signature_b64":"nseU8AzzXONHgvX0DDrZ+/UQBXUfHIZdojnC8pHjwGNj0Q6mdt4lyVeJrud6H9ATzYmbiHB7d6UmoCO62kaADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bdc36a22ede95a7f53e6efb94366cdcb279bbedb9cdb1c2abd22e52892b468e","last_reissued_at":"2026-07-05T06:16:15.986759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:15.986759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Causal Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Fuchun Sun, Libo Huang, Ruichu Cai, Yan Zeng, Zhifeng Hao","submitted_at":"2023-02-10T12:25:08Z","abstract_excerpt":"While Reinforcement Learning (RL) achieves tremendous success in sequential decision-making problems of many domains, it still faces key challenges of data inefficiency and the lack of interpretability. Interestingly, many researchers have leveraged insights from the causality literature recently, bringing forth flourishing works to unify the merits of causality and address well the challenges from RL. As such, it is of great necessity and significance to collate these Causal Reinforcement Learning (CRL) works, offer a review of CRL methods, and investigate the potential functionality from cau"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05209","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/2302.05209/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":"2302.05209","created_at":"2026-07-05T06:16:15.986821+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.05209v3","created_at":"2026-07-05T06:16:15.986821+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05209","created_at":"2026-07-05T06:16:15.986821+00:00"},{"alias_kind":"pith_short_12","alias_value":"FPODNIRO32K2","created_at":"2026-07-05T06:16:15.986821+00:00"},{"alias_kind":"pith_short_16","alias_value":"FPODNIRO32K2P5J6","created_at":"2026-07-05T06:16:15.986821+00:00"},{"alias_kind":"pith_short_8","alias_value":"FPODNIRO","created_at":"2026-07-05T06:16:15.986821+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06066","citing_title":"Causal Reinforcement Learning for Complex Card Games: A Magic The Gathering Benchmark","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FPODNIRO32K2P5J6N35ZINTM3S","json":"https://pith.science/pith/FPODNIRO32K2P5J6N35ZINTM3S.json","graph_json":"https://pith.science/api/pith-number/FPODNIRO32K2P5J6N35ZINTM3S/graph.json","events_json":"https://pith.science/api/pith-number/FPODNIRO32K2P5J6N35ZINTM3S/events.json","paper":"https://pith.science/paper/FPODNIRO"},"agent_actions":{"view_html":"https://pith.science/pith/FPODNIRO32K2P5J6N35ZINTM3S","download_json":"https://pith.science/pith/FPODNIRO32K2P5J6N35ZINTM3S.json","view_paper":"https://pith.science/paper/FPODNIRO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.05209&json=true","fetch_graph":"https://pith.science/api/pith-number/FPODNIRO32K2P5J6N35ZINTM3S/graph.json","fetch_events":"https://pith.science/api/pith-number/FPODNIRO32K2P5J6N35ZINTM3S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FPODNIRO32K2P5J6N35ZINTM3S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FPODNIRO32K2P5J6N35ZINTM3S/action/storage_attestation","attest_author":"https://pith.science/pith/FPODNIRO32K2P5J6N35ZINTM3S/action/author_attestation","sign_citation":"https://pith.science/pith/FPODNIRO32K2P5J6N35ZINTM3S/action/citation_signature","submit_replication":"https://pith.science/pith/FPODNIRO32K2P5J6N35ZINTM3S/action/replication_record"}},"created_at":"2026-07-05T06:16:15.986821+00:00","updated_at":"2026-07-05T06:16:15.986821+00:00"}