{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:3REYTHOMATRAECWXYH3MR5AO42","short_pith_number":"pith:3REYTHOM","schema_version":"1.0","canonical_sha256":"dc49899dcc04e2020ad7c1f6c8f40ee692813e8dbe0fd6092e7c11fc65d09214","source":{"kind":"arxiv","id":"1703.01274","version":2},"attestation_state":"computed","paper":{"title":"Actor-Critic Reinforcement Learning with Simultaneous Human Control and Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.RO"],"primary_cat":"cs.AI","authors_text":"Kory W. Mathewson, Patrick M. Pilarski","submitted_at":"2017-03-03T18:15:32Z","abstract_excerpt":"This paper contributes a first study into how different human users deliver simultaneous control and feedback signals during human-robot interaction. As part of this work, we formalize and present a general interactive learning framework for online cooperation between humans and reinforcement learning agents. In many human-machine interaction settings, there is a growing gap between the degrees-of-freedom of complex semi-autonomous systems and the number of human control channels. Simple human control and feedback mechanisms are required to close this gap and allow for better collaboration bet"},"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":"1703.01274","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-03T18:15:32Z","cross_cats_sorted":["cs.HC","cs.RO"],"title_canon_sha256":"fff59ffeb8d9b44358d03cd907984c20909781453a6745344f5b15a4914b2bc8","abstract_canon_sha256":"0009f483b6b0c0e01b3e46bbdb4e0a0e859bf67c08f75f23be93480199035401"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:41.688240Z","signature_b64":"EHY3IHSY4PJ/8xRM0WXS2rZU93mp93EMMNtKvC7UmI4CYQZ6IRcudso9spdJN6D/YFVslGCV6p70qp+RQOqsCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc49899dcc04e2020ad7c1f6c8f40ee692813e8dbe0fd6092e7c11fc65d09214","last_reissued_at":"2026-05-18T00:48:41.687826Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:41.687826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Actor-Critic Reinforcement Learning with Simultaneous Human Control and Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.RO"],"primary_cat":"cs.AI","authors_text":"Kory W. Mathewson, Patrick M. Pilarski","submitted_at":"2017-03-03T18:15:32Z","abstract_excerpt":"This paper contributes a first study into how different human users deliver simultaneous control and feedback signals during human-robot interaction. As part of this work, we formalize and present a general interactive learning framework for online cooperation between humans and reinforcement learning agents. In many human-machine interaction settings, there is a growing gap between the degrees-of-freedom of complex semi-autonomous systems and the number of human control channels. Simple human control and feedback mechanisms are required to close this gap and allow for better collaboration bet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.01274","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":"1703.01274","created_at":"2026-05-18T00:48:41.687885+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.01274v2","created_at":"2026-05-18T00:48:41.687885+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.01274","created_at":"2026-05-18T00:48:41.687885+00:00"},{"alias_kind":"pith_short_12","alias_value":"3REYTHOMATRA","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"3REYTHOMATRAECWX","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"3REYTHOM","created_at":"2026-05-18T12:30:58.224056+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/3REYTHOMATRAECWXYH3MR5AO42","json":"https://pith.science/pith/3REYTHOMATRAECWXYH3MR5AO42.json","graph_json":"https://pith.science/api/pith-number/3REYTHOMATRAECWXYH3MR5AO42/graph.json","events_json":"https://pith.science/api/pith-number/3REYTHOMATRAECWXYH3MR5AO42/events.json","paper":"https://pith.science/paper/3REYTHOM"},"agent_actions":{"view_html":"https://pith.science/pith/3REYTHOMATRAECWXYH3MR5AO42","download_json":"https://pith.science/pith/3REYTHOMATRAECWXYH3MR5AO42.json","view_paper":"https://pith.science/paper/3REYTHOM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.01274&json=true","fetch_graph":"https://pith.science/api/pith-number/3REYTHOMATRAECWXYH3MR5AO42/graph.json","fetch_events":"https://pith.science/api/pith-number/3REYTHOMATRAECWXYH3MR5AO42/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3REYTHOMATRAECWXYH3MR5AO42/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3REYTHOMATRAECWXYH3MR5AO42/action/storage_attestation","attest_author":"https://pith.science/pith/3REYTHOMATRAECWXYH3MR5AO42/action/author_attestation","sign_citation":"https://pith.science/pith/3REYTHOMATRAECWXYH3MR5AO42/action/citation_signature","submit_replication":"https://pith.science/pith/3REYTHOMATRAECWXYH3MR5AO42/action/replication_record"}},"created_at":"2026-05-18T00:48:41.687885+00:00","updated_at":"2026-05-18T00:48:41.687885+00:00"}