{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SH4QDD5EUV6OB2UPF3EFKSMC6Z","short_pith_number":"pith:SH4QDD5E","schema_version":"1.0","canonical_sha256":"91f9018fa4a57ce0ea8f2ec8554982f643b7e6e644359bfff21c1d541e9fbdbb","source":{"kind":"arxiv","id":"2204.12568","version":4},"attestation_state":"computed","paper":{"title":"Toward Policy Explanations for Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Kayla Boggess, Lu Feng, Sarit Kraus","submitted_at":"2022-04-26T20:07:08Z","abstract_excerpt":"Advances in multi-agent reinforcement learning (MARL) enable sequential decision making for a range of exciting multi-agent applications such as cooperative AI and autonomous driving. Explaining agent decisions is crucial for improving system transparency, increasing user satisfaction, and facilitating human-agent collaboration. However, existing works on explainable reinforcement learning mostly focus on the single-agent setting and are not suitable for addressing challenges posed by multi-agent environments. We present novel methods to generate two types of policy explanations for MARL: (i) "},"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":"2204.12568","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-04-26T20:07:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dd4584da29eda0e076cd1ae542626ba9c5ae07ff7dd9b86f4b8859b500c685a6","abstract_canon_sha256":"e2c75f451e114c35982b28c9f7600dc1fb1e275f87e682c4bc11ef5936403155"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:25:35.586333Z","signature_b64":"f1amF0+6fE/yxAPcqhKIFAXukxZA5/7KwEN9I0GBEZ3Y/gdy96MbzS6NhPiz8uuoOU2ehrCA/K+30N4WilJPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91f9018fa4a57ce0ea8f2ec8554982f643b7e6e644359bfff21c1d541e9fbdbb","last_reissued_at":"2026-07-05T04:25:35.585825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:25:35.585825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Policy Explanations for Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Kayla Boggess, Lu Feng, Sarit Kraus","submitted_at":"2022-04-26T20:07:08Z","abstract_excerpt":"Advances in multi-agent reinforcement learning (MARL) enable sequential decision making for a range of exciting multi-agent applications such as cooperative AI and autonomous driving. Explaining agent decisions is crucial for improving system transparency, increasing user satisfaction, and facilitating human-agent collaboration. However, existing works on explainable reinforcement learning mostly focus on the single-agent setting and are not suitable for addressing challenges posed by multi-agent environments. We present novel methods to generate two types of policy explanations for MARL: (i) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.12568","kind":"arxiv","version":4},"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/2204.12568/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":"2204.12568","created_at":"2026-07-05T04:25:35.585888+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.12568v4","created_at":"2026-07-05T04:25:35.585888+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.12568","created_at":"2026-07-05T04:25:35.585888+00:00"},{"alias_kind":"pith_short_12","alias_value":"SH4QDD5EUV6O","created_at":"2026-07-05T04:25:35.585888+00:00"},{"alias_kind":"pith_short_16","alias_value":"SH4QDD5EUV6OB2UP","created_at":"2026-07-05T04:25:35.585888+00:00"},{"alias_kind":"pith_short_8","alias_value":"SH4QDD5E","created_at":"2026-07-05T04:25:35.585888+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14360","citing_title":"Digital Guardians: The Past and The Future of Cyber-Physical Resilience","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SH4QDD5EUV6OB2UPF3EFKSMC6Z","json":"https://pith.science/pith/SH4QDD5EUV6OB2UPF3EFKSMC6Z.json","graph_json":"https://pith.science/api/pith-number/SH4QDD5EUV6OB2UPF3EFKSMC6Z/graph.json","events_json":"https://pith.science/api/pith-number/SH4QDD5EUV6OB2UPF3EFKSMC6Z/events.json","paper":"https://pith.science/paper/SH4QDD5E"},"agent_actions":{"view_html":"https://pith.science/pith/SH4QDD5EUV6OB2UPF3EFKSMC6Z","download_json":"https://pith.science/pith/SH4QDD5EUV6OB2UPF3EFKSMC6Z.json","view_paper":"https://pith.science/paper/SH4QDD5E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.12568&json=true","fetch_graph":"https://pith.science/api/pith-number/SH4QDD5EUV6OB2UPF3EFKSMC6Z/graph.json","fetch_events":"https://pith.science/api/pith-number/SH4QDD5EUV6OB2UPF3EFKSMC6Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SH4QDD5EUV6OB2UPF3EFKSMC6Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SH4QDD5EUV6OB2UPF3EFKSMC6Z/action/storage_attestation","attest_author":"https://pith.science/pith/SH4QDD5EUV6OB2UPF3EFKSMC6Z/action/author_attestation","sign_citation":"https://pith.science/pith/SH4QDD5EUV6OB2UPF3EFKSMC6Z/action/citation_signature","submit_replication":"https://pith.science/pith/SH4QDD5EUV6OB2UPF3EFKSMC6Z/action/replication_record"}},"created_at":"2026-07-05T04:25:35.585888+00:00","updated_at":"2026-07-05T04:25:35.585888+00:00"}