{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LKF2VICDIX2ELERR477WOOWQCX","short_pith_number":"pith:LKF2VICD","schema_version":"1.0","canonical_sha256":"5a8baaa04345f4459231e7ff673ad015cddd8133cf2e1f985b97a5614106dc3f","source":{"kind":"arxiv","id":"1712.07893","version":2},"attestation_state":"computed","paper":{"title":"A Deep Policy Inference Q-Network for Multi-Agent Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chun-Yi Lee, Shih-Yang Su, Tzu-Yun Shann, Yi-Hsiang Chang, Zhang-Wei Hong","submitted_at":"2017-12-21T11:53:35Z","abstract_excerpt":"We present DPIQN, a deep policy inference Q-network that targets multi-agent systems composed of controllable agents, collaborators, and opponents that interact with each other. We focus on one challenging issue in such systems---modeling agents with varying strategies---and propose to employ \"policy features\" learned from raw observations (e.g., raw images) of collaborators and opponents by inferring their policies. DPIQN incorporates the learned policy features as a hidden vector into its own deep Q-network (DQN), such that it is able to predict better Q values for the controllable agents th"},"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":"1712.07893","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-12-21T11:53:35Z","cross_cats_sorted":[],"title_canon_sha256":"95b17bd7512d10d86a4aa3102b09c6b266788d4e750d5cf2f39f10cc5214062c","abstract_canon_sha256":"6bfd33f9bc46105a330ef6d364e1857cc5b6b85292551a55a9d2df74b7e3d162"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:02.831252Z","signature_b64":"p9VgK32C1Oa+nVdaPpm4yf18T6mLIye0js/leMDf61SrJ3veFltZY4h9IUYrs+vUCNtNGDkjegcLaUxjpJGTAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a8baaa04345f4459231e7ff673ad015cddd8133cf2e1f985b97a5614106dc3f","last_reissued_at":"2026-05-18T00:19:02.830437Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:02.830437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Deep Policy Inference Q-Network for Multi-Agent Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chun-Yi Lee, Shih-Yang Su, Tzu-Yun Shann, Yi-Hsiang Chang, Zhang-Wei Hong","submitted_at":"2017-12-21T11:53:35Z","abstract_excerpt":"We present DPIQN, a deep policy inference Q-network that targets multi-agent systems composed of controllable agents, collaborators, and opponents that interact with each other. We focus on one challenging issue in such systems---modeling agents with varying strategies---and propose to employ \"policy features\" learned from raw observations (e.g., raw images) of collaborators and opponents by inferring their policies. DPIQN incorporates the learned policy features as a hidden vector into its own deep Q-network (DQN), such that it is able to predict better Q values for the controllable agents th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.07893","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":""},"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":"1712.07893","created_at":"2026-05-18T00:19:02.830565+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.07893v2","created_at":"2026-05-18T00:19:02.830565+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.07893","created_at":"2026-05-18T00:19:02.830565+00:00"},{"alias_kind":"pith_short_12","alias_value":"LKF2VICDIX2E","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LKF2VICDIX2ELERR","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LKF2VICD","created_at":"2026-05-18T12:31:28.150371+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/LKF2VICDIX2ELERR477WOOWQCX","json":"https://pith.science/pith/LKF2VICDIX2ELERR477WOOWQCX.json","graph_json":"https://pith.science/api/pith-number/LKF2VICDIX2ELERR477WOOWQCX/graph.json","events_json":"https://pith.science/api/pith-number/LKF2VICDIX2ELERR477WOOWQCX/events.json","paper":"https://pith.science/paper/LKF2VICD"},"agent_actions":{"view_html":"https://pith.science/pith/LKF2VICDIX2ELERR477WOOWQCX","download_json":"https://pith.science/pith/LKF2VICDIX2ELERR477WOOWQCX.json","view_paper":"https://pith.science/paper/LKF2VICD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.07893&json=true","fetch_graph":"https://pith.science/api/pith-number/LKF2VICDIX2ELERR477WOOWQCX/graph.json","fetch_events":"https://pith.science/api/pith-number/LKF2VICDIX2ELERR477WOOWQCX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LKF2VICDIX2ELERR477WOOWQCX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LKF2VICDIX2ELERR477WOOWQCX/action/storage_attestation","attest_author":"https://pith.science/pith/LKF2VICDIX2ELERR477WOOWQCX/action/author_attestation","sign_citation":"https://pith.science/pith/LKF2VICDIX2ELERR477WOOWQCX/action/citation_signature","submit_replication":"https://pith.science/pith/LKF2VICDIX2ELERR477WOOWQCX/action/replication_record"}},"created_at":"2026-05-18T00:19:02.830565+00:00","updated_at":"2026-05-18T00:19:02.830565+00:00"}