{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:LKF2VICDIX2ELERR477WOOWQCX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6bfd33f9bc46105a330ef6d364e1857cc5b6b85292551a55a9d2df74b7e3d162","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-12-21T11:53:35Z","title_canon_sha256":"95b17bd7512d10d86a4aa3102b09c6b266788d4e750d5cf2f39f10cc5214062c"},"schema_version":"1.0","source":{"id":"1712.07893","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.07893","created_at":"2026-05-18T00:19:02Z"},{"alias_kind":"arxiv_version","alias_value":"1712.07893v2","created_at":"2026-05-18T00:19:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.07893","created_at":"2026-05-18T00:19:02Z"},{"alias_kind":"pith_short_12","alias_value":"LKF2VICDIX2E","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LKF2VICDIX2ELERR","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LKF2VICD","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:ec87412ad195fd573a074326b72eceb74242d3d8a85e07e1ed552b72ad9a45c7","target":"graph","created_at":"2026-05-18T00:19:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Chun-Yi Lee, Shih-Yang Su, Tzu-Yun Shann, Yi-Hsiang Chang, Zhang-Wei Hong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-12-21T11:53:35Z","title":"A Deep Policy Inference Q-Network for Multi-Agent Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.07893","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c09ff0ce7de7a2e12440cede403b37882e19804344dd0e062ae46d1f04a2f4f6","target":"record","created_at":"2026-05-18T00:19:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6bfd33f9bc46105a330ef6d364e1857cc5b6b85292551a55a9d2df74b7e3d162","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-12-21T11:53:35Z","title_canon_sha256":"95b17bd7512d10d86a4aa3102b09c6b266788d4e750d5cf2f39f10cc5214062c"},"schema_version":"1.0","source":{"id":"1712.07893","kind":"arxiv","version":2}},"canonical_sha256":"5a8baaa04345f4459231e7ff673ad015cddd8133cf2e1f985b97a5614106dc3f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a8baaa04345f4459231e7ff673ad015cddd8133cf2e1f985b97a5614106dc3f","first_computed_at":"2026-05-18T00:19:02.830437Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:02.830437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p9VgK32C1Oa+nVdaPpm4yf18T6mLIye0js/leMDf61SrJ3veFltZY4h9IUYrs+vUCNtNGDkjegcLaUxjpJGTAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:02.831252Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.07893","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c09ff0ce7de7a2e12440cede403b37882e19804344dd0e062ae46d1f04a2f4f6","sha256:ec87412ad195fd573a074326b72eceb74242d3d8a85e07e1ed552b72ad9a45c7"],"state_sha256":"c6ee3ac4310271c5e5c231ccab6f7f82b4da59678646c9f5b2529396a69f9107"}