{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4QGAMCCR63HRAQYN6GWTMPKSRV","short_pith_number":"pith:4QGAMCCR","schema_version":"1.0","canonical_sha256":"e40c060851f6cf10430df1ad363d528d4e1249eb31295d81a8b636a8dfe6287d","source":{"kind":"arxiv","id":"2406.08002","version":2},"attestation_state":"computed","paper":{"title":"Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Anji Liu, Fanqi Kong, Song-Chun Zhu, Xue Feng, Yaodong Yang, Yizhe Huang","submitted_at":"2024-06-12T08:48:06Z","abstract_excerpt":"Despite the recent successes of multi-agent reinforcement learning (MARL) algorithms, efficiently adapting to co-players in mixed-motive environments remains a significant challenge. One feasible approach is to hierarchically model co-players' behavior based on inferring their characteristics. However, these methods often encounter difficulties in efficient reasoning and utilization of inferred information. To address these issues, we propose Hierarchical Opponent modeling and Planning (HOP), a novel multi-agent decision-making algorithm that enables few-shot adaptation to unseen policies in m"},"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":"2406.08002","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-12T08:48:06Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"5f950ff497500a742635506d59b27004e502830c16b7c2ce2d69b5910c76edc1","abstract_canon_sha256":"75bac20a0a7603ea790f34ade9e21063dba6a8b0a83fbbe4338d71203ebd9da5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:10.798686Z","signature_b64":"DHRbmLxkc8wDU5h5edcUq5nE53kphILKuHQ7LJr04M1o1JXWzjtWtP3338A5kPbUvTGtzJ/xMpfgL7PysYOLDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e40c060851f6cf10430df1ad363d528d4e1249eb31295d81a8b636a8dfe6287d","last_reissued_at":"2026-07-05T08:43:10.798189Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:10.798189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Anji Liu, Fanqi Kong, Song-Chun Zhu, Xue Feng, Yaodong Yang, Yizhe Huang","submitted_at":"2024-06-12T08:48:06Z","abstract_excerpt":"Despite the recent successes of multi-agent reinforcement learning (MARL) algorithms, efficiently adapting to co-players in mixed-motive environments remains a significant challenge. One feasible approach is to hierarchically model co-players' behavior based on inferring their characteristics. However, these methods often encounter difficulties in efficient reasoning and utilization of inferred information. To address these issues, we propose Hierarchical Opponent modeling and Planning (HOP), a novel multi-agent decision-making algorithm that enables few-shot adaptation to unseen policies in m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08002","kind":"arxiv","version":2},"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/2406.08002/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":"2406.08002","created_at":"2026-07-05T08:43:10.798249+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.08002v2","created_at":"2026-07-05T08:43:10.798249+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08002","created_at":"2026-07-05T08:43:10.798249+00:00"},{"alias_kind":"pith_short_12","alias_value":"4QGAMCCR63HR","created_at":"2026-07-05T08:43:10.798249+00:00"},{"alias_kind":"pith_short_16","alias_value":"4QGAMCCR63HRAQYN","created_at":"2026-07-05T08:43:10.798249+00:00"},{"alias_kind":"pith_short_8","alias_value":"4QGAMCCR","created_at":"2026-07-05T08:43:10.798249+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.00581","citing_title":"Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4QGAMCCR63HRAQYN6GWTMPKSRV","json":"https://pith.science/pith/4QGAMCCR63HRAQYN6GWTMPKSRV.json","graph_json":"https://pith.science/api/pith-number/4QGAMCCR63HRAQYN6GWTMPKSRV/graph.json","events_json":"https://pith.science/api/pith-number/4QGAMCCR63HRAQYN6GWTMPKSRV/events.json","paper":"https://pith.science/paper/4QGAMCCR"},"agent_actions":{"view_html":"https://pith.science/pith/4QGAMCCR63HRAQYN6GWTMPKSRV","download_json":"https://pith.science/pith/4QGAMCCR63HRAQYN6GWTMPKSRV.json","view_paper":"https://pith.science/paper/4QGAMCCR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.08002&json=true","fetch_graph":"https://pith.science/api/pith-number/4QGAMCCR63HRAQYN6GWTMPKSRV/graph.json","fetch_events":"https://pith.science/api/pith-number/4QGAMCCR63HRAQYN6GWTMPKSRV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4QGAMCCR63HRAQYN6GWTMPKSRV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4QGAMCCR63HRAQYN6GWTMPKSRV/action/storage_attestation","attest_author":"https://pith.science/pith/4QGAMCCR63HRAQYN6GWTMPKSRV/action/author_attestation","sign_citation":"https://pith.science/pith/4QGAMCCR63HRAQYN6GWTMPKSRV/action/citation_signature","submit_replication":"https://pith.science/pith/4QGAMCCR63HRAQYN6GWTMPKSRV/action/replication_record"}},"created_at":"2026-07-05T08:43:10.798249+00:00","updated_at":"2026-07-05T08:43:10.798249+00:00"}