{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:2C357K7S53VGMAKTMFPRW3BY4F","short_pith_number":"pith:2C357K7S","schema_version":"1.0","canonical_sha256":"d0b7dfabf2eeea660153615f1b6c38e17db27ed52b1258c13f4ed53d78720a46","source":{"kind":"arxiv","id":"1702.07492","version":1},"attestation_state":"computed","paper":{"title":"Robot gains Social Intelligence through Multimodal Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.RO","authors_text":"Ahmed Hussain Qureshi, Hiroshi Ishiguro, Yuichiro Yoshikawa, Yutaka Nakamura","submitted_at":"2017-02-24T08:30:43Z","abstract_excerpt":"For robots to coexist with humans in a social world like ours, it is crucial that they possess human-like social interaction skills. Programming a robot to possess such skills is a challenging task. In this paper, we propose a Multimodal Deep Q-Network (MDQN) to enable a robot to learn human-like interaction skills through a trial and error method. This paper aims to develop a robot that gathers data during its interaction with a human and learns human interaction behaviour from the high-dimensional sensory information using end-to-end reinforcement learning. This paper demonstrates that the r"},"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":"1702.07492","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-02-24T08:30:43Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"94a9bbce62241cea3bf4decc00961b9685bc383cd98d71650130a83c90228428","abstract_canon_sha256":"60649e25a5cda0d8c3755ec17e909c51de434917f925d84cde742ec954621542"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:03.169860Z","signature_b64":"sltlSEKfIiCfjPzICgNP91MPjwjliTzHkmkRcB0t8t2+ZcOBK5yUY6YipE/Mn5CaKiUU7ecEoJ/uiX4+Y8kpAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0b7dfabf2eeea660153615f1b6c38e17db27ed52b1258c13f4ed53d78720a46","last_reissued_at":"2026-05-18T00:50:03.169329Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:03.169329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robot gains Social Intelligence through Multimodal Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.RO","authors_text":"Ahmed Hussain Qureshi, Hiroshi Ishiguro, Yuichiro Yoshikawa, Yutaka Nakamura","submitted_at":"2017-02-24T08:30:43Z","abstract_excerpt":"For robots to coexist with humans in a social world like ours, it is crucial that they possess human-like social interaction skills. Programming a robot to possess such skills is a challenging task. In this paper, we propose a Multimodal Deep Q-Network (MDQN) to enable a robot to learn human-like interaction skills through a trial and error method. This paper aims to develop a robot that gathers data during its interaction with a human and learns human interaction behaviour from the high-dimensional sensory information using end-to-end reinforcement learning. This paper demonstrates that the r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.07492","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":""},"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":"1702.07492","created_at":"2026-05-18T00:50:03.169423+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.07492v1","created_at":"2026-05-18T00:50:03.169423+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.07492","created_at":"2026-05-18T00:50:03.169423+00:00"},{"alias_kind":"pith_short_12","alias_value":"2C357K7S53VG","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_16","alias_value":"2C357K7S53VGMAKT","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_8","alias_value":"2C357K7S","created_at":"2026-05-18T12:30:55.937587+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/2C357K7S53VGMAKTMFPRW3BY4F","json":"https://pith.science/pith/2C357K7S53VGMAKTMFPRW3BY4F.json","graph_json":"https://pith.science/api/pith-number/2C357K7S53VGMAKTMFPRW3BY4F/graph.json","events_json":"https://pith.science/api/pith-number/2C357K7S53VGMAKTMFPRW3BY4F/events.json","paper":"https://pith.science/paper/2C357K7S"},"agent_actions":{"view_html":"https://pith.science/pith/2C357K7S53VGMAKTMFPRW3BY4F","download_json":"https://pith.science/pith/2C357K7S53VGMAKTMFPRW3BY4F.json","view_paper":"https://pith.science/paper/2C357K7S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.07492&json=true","fetch_graph":"https://pith.science/api/pith-number/2C357K7S53VGMAKTMFPRW3BY4F/graph.json","fetch_events":"https://pith.science/api/pith-number/2C357K7S53VGMAKTMFPRW3BY4F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2C357K7S53VGMAKTMFPRW3BY4F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2C357K7S53VGMAKTMFPRW3BY4F/action/storage_attestation","attest_author":"https://pith.science/pith/2C357K7S53VGMAKTMFPRW3BY4F/action/author_attestation","sign_citation":"https://pith.science/pith/2C357K7S53VGMAKTMFPRW3BY4F/action/citation_signature","submit_replication":"https://pith.science/pith/2C357K7S53VGMAKTMFPRW3BY4F/action/replication_record"}},"created_at":"2026-05-18T00:50:03.169423+00:00","updated_at":"2026-05-18T00:50:03.169423+00:00"}