{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:AD7A6EJESUASLHIUD7E2PEET2T","short_pith_number":"pith:AD7A6EJE","schema_version":"1.0","canonical_sha256":"00fe0f11249501259d141fc9a79093d4ff1b82ddbbdfc2505c30ea2899b4117b","source":{"kind":"arxiv","id":"1807.09991","version":1},"attestation_state":"computed","paper":{"title":"Multi-modal Feedback for Affordance-driven Interactive Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Francisco Cruz, German I. Parisi, Stefan Wermter","submitted_at":"2018-07-26T07:48:33Z","abstract_excerpt":"Interactive reinforcement learning (IRL) extends traditional reinforcement learning (RL) by allowing an agent to interact with parent-like trainers during a task. In this paper, we present an IRL approach using dynamic audio-visual input in terms of vocal commands and hand gestures as feedback. Our architecture integrates multi-modal information to provide robust commands from multiple sensory cues along with a confidence value indicating the trustworthiness of the feedback. The integration process also considers the case in which the two modalities convey incongruent information. Additionally"},"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":"1807.09991","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-07-26T07:48:33Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"3d8b21d238e0cbedaeea43b3002c6ba1a38b1fdecc770b61974236b9ff1cb9b1","abstract_canon_sha256":"a58733f84291f6011048aeabb2fd2af459f2adce2faebd028852fe2c6488197b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:45.790952Z","signature_b64":"+GrBddHEHJaMS6PNHIkuIQHuaXAZjD4DkgnZAFgm3ubRwg5mXGKKNteN7fPurkPb8D1lIaqFp7TcJDhXPtmLAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00fe0f11249501259d141fc9a79093d4ff1b82ddbbdfc2505c30ea2899b4117b","last_reissued_at":"2026-05-18T00:09:45.790287Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:45.790287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-modal Feedback for Affordance-driven Interactive Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Francisco Cruz, German I. Parisi, Stefan Wermter","submitted_at":"2018-07-26T07:48:33Z","abstract_excerpt":"Interactive reinforcement learning (IRL) extends traditional reinforcement learning (RL) by allowing an agent to interact with parent-like trainers during a task. In this paper, we present an IRL approach using dynamic audio-visual input in terms of vocal commands and hand gestures as feedback. Our architecture integrates multi-modal information to provide robust commands from multiple sensory cues along with a confidence value indicating the trustworthiness of the feedback. The integration process also considers the case in which the two modalities convey incongruent information. Additionally"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.09991","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":"1807.09991","created_at":"2026-05-18T00:09:45.790403+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.09991v1","created_at":"2026-05-18T00:09:45.790403+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.09991","created_at":"2026-05-18T00:09:45.790403+00:00"},{"alias_kind":"pith_short_12","alias_value":"AD7A6EJESUAS","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"AD7A6EJESUASLHIU","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"AD7A6EJE","created_at":"2026-05-18T12:32:13.499390+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/AD7A6EJESUASLHIUD7E2PEET2T","json":"https://pith.science/pith/AD7A6EJESUASLHIUD7E2PEET2T.json","graph_json":"https://pith.science/api/pith-number/AD7A6EJESUASLHIUD7E2PEET2T/graph.json","events_json":"https://pith.science/api/pith-number/AD7A6EJESUASLHIUD7E2PEET2T/events.json","paper":"https://pith.science/paper/AD7A6EJE"},"agent_actions":{"view_html":"https://pith.science/pith/AD7A6EJESUASLHIUD7E2PEET2T","download_json":"https://pith.science/pith/AD7A6EJESUASLHIUD7E2PEET2T.json","view_paper":"https://pith.science/paper/AD7A6EJE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.09991&json=true","fetch_graph":"https://pith.science/api/pith-number/AD7A6EJESUASLHIUD7E2PEET2T/graph.json","fetch_events":"https://pith.science/api/pith-number/AD7A6EJESUASLHIUD7E2PEET2T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AD7A6EJESUASLHIUD7E2PEET2T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AD7A6EJESUASLHIUD7E2PEET2T/action/storage_attestation","attest_author":"https://pith.science/pith/AD7A6EJESUASLHIUD7E2PEET2T/action/author_attestation","sign_citation":"https://pith.science/pith/AD7A6EJESUASLHIUD7E2PEET2T/action/citation_signature","submit_replication":"https://pith.science/pith/AD7A6EJESUASLHIUD7E2PEET2T/action/replication_record"}},"created_at":"2026-05-18T00:09:45.790403+00:00","updated_at":"2026-05-18T00:09:45.790403+00:00"}