{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KFGKEPJAT6W2R3GEX4U4RON745","short_pith_number":"pith:KFGKEPJA","schema_version":"1.0","canonical_sha256":"514ca23d209fada8ecc4bf29c8b9bfe7578ea9ba4e2ca46df064b55dd1036d69","source":{"kind":"arxiv","id":"2210.04723","version":5},"attestation_state":"computed","paper":{"title":"Experiential Explanations for Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Amal Alabdulkarim, Gennie Mansi, Kaely Hall, Madhuri Singh, Mark O. Riedl, Upol Ehsan","submitted_at":"2022-10-10T14:27:53Z","abstract_excerpt":"Reinforcement learning (RL) systems can be complex and non-interpretable, making it challenging for non-AI experts to understand or intervene in their decisions. This is due in part to the sequential nature of RL in which actions are chosen because of their likelihood of obtaining future rewards. However, RL agents discard the qualitative features of their training, making it difficult to recover user-understandable information for \"why\" an action is chosen. We propose a technique Experiential Explanations to generate counterfactual explanations by training influence predictors along with the "},"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":"2210.04723","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-10-10T14:27:53Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"c62c0de35da88261a3c681311eb9d6fb65da4d70ce5fd86efae216bf1581aa72","abstract_canon_sha256":"ce481f17595f7afb5ccebebac09af0fcbcb40258573ccfd6b48c45c02e3126b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:02.115731Z","signature_b64":"N7nS/K3fUL+2lr8Z8w5CSYZeVtToKZVx6Py3cYmztkCTbBZ2+k9GBvUw/Zhqs2X6Js/TdsRC3ON9ePpVIp75CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"514ca23d209fada8ecc4bf29c8b9bfe7578ea9ba4e2ca46df064b55dd1036d69","last_reissued_at":"2026-07-05T10:49:02.115231Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:02.115231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Experiential Explanations for Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Amal Alabdulkarim, Gennie Mansi, Kaely Hall, Madhuri Singh, Mark O. Riedl, Upol Ehsan","submitted_at":"2022-10-10T14:27:53Z","abstract_excerpt":"Reinforcement learning (RL) systems can be complex and non-interpretable, making it challenging for non-AI experts to understand or intervene in their decisions. This is due in part to the sequential nature of RL in which actions are chosen because of their likelihood of obtaining future rewards. However, RL agents discard the qualitative features of their training, making it difficult to recover user-understandable information for \"why\" an action is chosen. We propose a technique Experiential Explanations to generate counterfactual explanations by training influence predictors along with the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04723","kind":"arxiv","version":5},"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/2210.04723/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":"2210.04723","created_at":"2026-07-05T10:49:02.115289+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.04723v5","created_at":"2026-07-05T10:49:02.115289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04723","created_at":"2026-07-05T10:49:02.115289+00:00"},{"alias_kind":"pith_short_12","alias_value":"KFGKEPJAT6W2","created_at":"2026-07-05T10:49:02.115289+00:00"},{"alias_kind":"pith_short_16","alias_value":"KFGKEPJAT6W2R3GE","created_at":"2026-07-05T10:49:02.115289+00:00"},{"alias_kind":"pith_short_8","alias_value":"KFGKEPJA","created_at":"2026-07-05T10:49:02.115289+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.11708","citing_title":"Unveiling the Black Box: A Multi-Layer Framework for Explaining Reinforcement Learning-Based Cyber Agents","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KFGKEPJAT6W2R3GEX4U4RON745","json":"https://pith.science/pith/KFGKEPJAT6W2R3GEX4U4RON745.json","graph_json":"https://pith.science/api/pith-number/KFGKEPJAT6W2R3GEX4U4RON745/graph.json","events_json":"https://pith.science/api/pith-number/KFGKEPJAT6W2R3GEX4U4RON745/events.json","paper":"https://pith.science/paper/KFGKEPJA"},"agent_actions":{"view_html":"https://pith.science/pith/KFGKEPJAT6W2R3GEX4U4RON745","download_json":"https://pith.science/pith/KFGKEPJAT6W2R3GEX4U4RON745.json","view_paper":"https://pith.science/paper/KFGKEPJA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.04723&json=true","fetch_graph":"https://pith.science/api/pith-number/KFGKEPJAT6W2R3GEX4U4RON745/graph.json","fetch_events":"https://pith.science/api/pith-number/KFGKEPJAT6W2R3GEX4U4RON745/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KFGKEPJAT6W2R3GEX4U4RON745/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KFGKEPJAT6W2R3GEX4U4RON745/action/storage_attestation","attest_author":"https://pith.science/pith/KFGKEPJAT6W2R3GEX4U4RON745/action/author_attestation","sign_citation":"https://pith.science/pith/KFGKEPJAT6W2R3GEX4U4RON745/action/citation_signature","submit_replication":"https://pith.science/pith/KFGKEPJAT6W2R3GEX4U4RON745/action/replication_record"}},"created_at":"2026-07-05T10:49:02.115289+00:00","updated_at":"2026-07-05T10:49:02.115289+00:00"}