{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GXFSMDCR4HYFEG4QCDGPGYBOVS","short_pith_number":"pith:GXFSMDCR","schema_version":"1.0","canonical_sha256":"35cb260c51e1f0521b9010ccf3602eac8835770ac2109ea04958ce2da0c120c0","source":{"kind":"arxiv","id":"2503.04679","version":1},"attestation_state":"computed","paper":{"title":"Multi-Agent Inverse Q-Learning from Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.MA","authors_text":"Adam Khoja, Dhruv Kumar, Erdem B{\\i}y{\\i}k, Nathaniel Haynam, Vivek Myers","submitted_at":"2025-03-06T18:22:29Z","abstract_excerpt":"When reward functions are hand-designed, deep reinforcement learning algorithms often suffer from reward misspecification, causing them to learn suboptimal policies in terms of the intended task objectives. In the single-agent case, inverse reinforcement learning (IRL) techniques attempt to address this issue by inferring the reward function from expert demonstrations. However, in multi-agent problems, misalignment between the learned and true objectives is exacerbated due to increased environment non-stationarity and variance that scales with multiple agents. As such, in multi-agent general-s"},"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":"2503.04679","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2025-03-06T18:22:29Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"d5c22d5278e4cbb8a7e4520bc22d18ad9f603212efcdc828cb6ef62c6995035a","abstract_canon_sha256":"e371d954fb55b8145272b0ef908669836e9526183454433387899b730bc745da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:45.014403Z","signature_b64":"psNPjI8vMD58JyDb8k7BuC758elRB/aI+DjAknd+/NgBXWKZ2MiV3lT/73knsJ99pNBAlaJAzelRaJ9GIBdUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35cb260c51e1f0521b9010ccf3602eac8835770ac2109ea04958ce2da0c120c0","last_reissued_at":"2026-07-05T10:25:45.013956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:45.013956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent Inverse Q-Learning from Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.MA","authors_text":"Adam Khoja, Dhruv Kumar, Erdem B{\\i}y{\\i}k, Nathaniel Haynam, Vivek Myers","submitted_at":"2025-03-06T18:22:29Z","abstract_excerpt":"When reward functions are hand-designed, deep reinforcement learning algorithms often suffer from reward misspecification, causing them to learn suboptimal policies in terms of the intended task objectives. In the single-agent case, inverse reinforcement learning (IRL) techniques attempt to address this issue by inferring the reward function from expert demonstrations. However, in multi-agent problems, misalignment between the learned and true objectives is exacerbated due to increased environment non-stationarity and variance that scales with multiple agents. As such, in multi-agent general-s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04679","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/2503.04679/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":"2503.04679","created_at":"2026-07-05T10:25:45.014014+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.04679v1","created_at":"2026-07-05T10:25:45.014014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04679","created_at":"2026-07-05T10:25:45.014014+00:00"},{"alias_kind":"pith_short_12","alias_value":"GXFSMDCR4HYF","created_at":"2026-07-05T10:25:45.014014+00:00"},{"alias_kind":"pith_short_16","alias_value":"GXFSMDCR4HYFEG4Q","created_at":"2026-07-05T10:25:45.014014+00:00"},{"alias_kind":"pith_short_8","alias_value":"GXFSMDCR","created_at":"2026-07-05T10:25:45.014014+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GXFSMDCR4HYFEG4QCDGPGYBOVS","json":"https://pith.science/pith/GXFSMDCR4HYFEG4QCDGPGYBOVS.json","graph_json":"https://pith.science/api/pith-number/GXFSMDCR4HYFEG4QCDGPGYBOVS/graph.json","events_json":"https://pith.science/api/pith-number/GXFSMDCR4HYFEG4QCDGPGYBOVS/events.json","paper":"https://pith.science/paper/GXFSMDCR"},"agent_actions":{"view_html":"https://pith.science/pith/GXFSMDCR4HYFEG4QCDGPGYBOVS","download_json":"https://pith.science/pith/GXFSMDCR4HYFEG4QCDGPGYBOVS.json","view_paper":"https://pith.science/paper/GXFSMDCR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.04679&json=true","fetch_graph":"https://pith.science/api/pith-number/GXFSMDCR4HYFEG4QCDGPGYBOVS/graph.json","fetch_events":"https://pith.science/api/pith-number/GXFSMDCR4HYFEG4QCDGPGYBOVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GXFSMDCR4HYFEG4QCDGPGYBOVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GXFSMDCR4HYFEG4QCDGPGYBOVS/action/storage_attestation","attest_author":"https://pith.science/pith/GXFSMDCR4HYFEG4QCDGPGYBOVS/action/author_attestation","sign_citation":"https://pith.science/pith/GXFSMDCR4HYFEG4QCDGPGYBOVS/action/citation_signature","submit_replication":"https://pith.science/pith/GXFSMDCR4HYFEG4QCDGPGYBOVS/action/replication_record"}},"created_at":"2026-07-05T10:25:45.014014+00:00","updated_at":"2026-07-05T10:25:45.014014+00:00"}