{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:3REYTHOMATRAECWXYH3MR5AO42","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":"0009f483b6b0c0e01b3e46bbdb4e0a0e859bf67c08f75f23be93480199035401","cross_cats_sorted":["cs.HC","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-03T18:15:32Z","title_canon_sha256":"fff59ffeb8d9b44358d03cd907984c20909781453a6745344f5b15a4914b2bc8"},"schema_version":"1.0","source":{"id":"1703.01274","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.01274","created_at":"2026-05-18T00:48:41Z"},{"alias_kind":"arxiv_version","alias_value":"1703.01274v2","created_at":"2026-05-18T00:48:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.01274","created_at":"2026-05-18T00:48:41Z"},{"alias_kind":"pith_short_12","alias_value":"3REYTHOMATRA","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3REYTHOMATRAECWX","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3REYTHOM","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:a51afc733ab808995a4bbeb756eec067329bc86877fcffd47aa329d0bc99cf86","target":"graph","created_at":"2026-05-18T00:48:41Z","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":"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","authors_text":"Kory W. Mathewson, Patrick M. Pilarski","cross_cats":["cs.HC","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-03T18:15:32Z","title":"Actor-Critic Reinforcement Learning with Simultaneous Human Control and Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.01274","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:df361f8f9bcbaeca3417f2523979395a56bce99b22bd63d58dc760172066eb8e","target":"record","created_at":"2026-05-18T00:48:41Z","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":"0009f483b6b0c0e01b3e46bbdb4e0a0e859bf67c08f75f23be93480199035401","cross_cats_sorted":["cs.HC","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-03T18:15:32Z","title_canon_sha256":"fff59ffeb8d9b44358d03cd907984c20909781453a6745344f5b15a4914b2bc8"},"schema_version":"1.0","source":{"id":"1703.01274","kind":"arxiv","version":2}},"canonical_sha256":"dc49899dcc04e2020ad7c1f6c8f40ee692813e8dbe0fd6092e7c11fc65d09214","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc49899dcc04e2020ad7c1f6c8f40ee692813e8dbe0fd6092e7c11fc65d09214","first_computed_at":"2026-05-18T00:48:41.687826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:48:41.687826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EHY3IHSY4PJ/8xRM0WXS2rZU93mp93EMMNtKvC7UmI4CYQZ6IRcudso9spdJN6D/YFVslGCV6p70qp+RQOqsCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:48:41.688240Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.01274","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df361f8f9bcbaeca3417f2523979395a56bce99b22bd63d58dc760172066eb8e","sha256:a51afc733ab808995a4bbeb756eec067329bc86877fcffd47aa329d0bc99cf86"],"state_sha256":"1847592a3ac7649b9b378925bfbe61eb23197da6e35019b49ebc17b6b2263aaa"}