{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XLBYOIYUUVZCULEQCKHHXETS7R","short_pith_number":"pith:XLBYOIYU","schema_version":"1.0","canonical_sha256":"bac3872314a5722a2c90128e7b9272fc74074ba8ca6f03d0a145106001b90f44","source":{"kind":"arxiv","id":"2201.01448","version":1},"attestation_state":"computed","paper":{"title":"Conditional Imitation Learning for Multi-Agent Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Andy Shih, Dorsa Sadigh, Stefano Ermon","submitted_at":"2022-01-05T04:40:13Z","abstract_excerpt":"While advances in multi-agent learning have enabled the training of increasingly complex agents, most existing techniques produce a final policy that is not designed to adapt to a new partner's strategy. However, we would like our AI agents to adjust their strategy based on the strategies of those around them. In this work, we study the problem of conditional multi-agent imitation learning, where we have access to joint trajectory demonstrations at training time, and we must interact with and adapt to new partners at test time. This setting is challenging because we must infer a new partner'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":"2201.01448","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-05T04:40:13Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"56c05adf2ddb0b38c90bc5c95a1c6e842c02f8856ce29fc7402a18e9c5900388","abstract_canon_sha256":"dde773e5295bf9a6c25df1cb20b5f27e1fa6887242c5ef150465489732482833"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:46:05.728631Z","signature_b64":"vY3P0G7gFAwIZLMagCDeYTUGJiQQ5LjZqF6WihIntsIOysPBJYAjPVVyUDw1RVUP353gJ3Vz48myjO8q/F8vBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bac3872314a5722a2c90128e7b9272fc74074ba8ca6f03d0a145106001b90f44","last_reissued_at":"2026-07-05T03:46:05.728195Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:46:05.728195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conditional Imitation Learning for Multi-Agent Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Andy Shih, Dorsa Sadigh, Stefano Ermon","submitted_at":"2022-01-05T04:40:13Z","abstract_excerpt":"While advances in multi-agent learning have enabled the training of increasingly complex agents, most existing techniques produce a final policy that is not designed to adapt to a new partner's strategy. However, we would like our AI agents to adjust their strategy based on the strategies of those around them. In this work, we study the problem of conditional multi-agent imitation learning, where we have access to joint trajectory demonstrations at training time, and we must interact with and adapt to new partners at test time. This setting is challenging because we must infer a new partner's "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.01448","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/2201.01448/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":"2201.01448","created_at":"2026-07-05T03:46:05.728257+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.01448v1","created_at":"2026-07-05T03:46:05.728257+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.01448","created_at":"2026-07-05T03:46:05.728257+00:00"},{"alias_kind":"pith_short_12","alias_value":"XLBYOIYUUVZC","created_at":"2026-07-05T03:46:05.728257+00:00"},{"alias_kind":"pith_short_16","alias_value":"XLBYOIYUUVZCULEQ","created_at":"2026-07-05T03:46:05.728257+00:00"},{"alias_kind":"pith_short_8","alias_value":"XLBYOIYU","created_at":"2026-07-05T03:46:05.728257+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/XLBYOIYUUVZCULEQCKHHXETS7R","json":"https://pith.science/pith/XLBYOIYUUVZCULEQCKHHXETS7R.json","graph_json":"https://pith.science/api/pith-number/XLBYOIYUUVZCULEQCKHHXETS7R/graph.json","events_json":"https://pith.science/api/pith-number/XLBYOIYUUVZCULEQCKHHXETS7R/events.json","paper":"https://pith.science/paper/XLBYOIYU"},"agent_actions":{"view_html":"https://pith.science/pith/XLBYOIYUUVZCULEQCKHHXETS7R","download_json":"https://pith.science/pith/XLBYOIYUUVZCULEQCKHHXETS7R.json","view_paper":"https://pith.science/paper/XLBYOIYU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.01448&json=true","fetch_graph":"https://pith.science/api/pith-number/XLBYOIYUUVZCULEQCKHHXETS7R/graph.json","fetch_events":"https://pith.science/api/pith-number/XLBYOIYUUVZCULEQCKHHXETS7R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XLBYOIYUUVZCULEQCKHHXETS7R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XLBYOIYUUVZCULEQCKHHXETS7R/action/storage_attestation","attest_author":"https://pith.science/pith/XLBYOIYUUVZCULEQCKHHXETS7R/action/author_attestation","sign_citation":"https://pith.science/pith/XLBYOIYUUVZCULEQCKHHXETS7R/action/citation_signature","submit_replication":"https://pith.science/pith/XLBYOIYUUVZCULEQCKHHXETS7R/action/replication_record"}},"created_at":"2026-07-05T03:46:05.728257+00:00","updated_at":"2026-07-05T03:46:05.728257+00:00"}