{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:BYGBCNFB4JII7TL2RL5VMD47BY","short_pith_number":"pith:BYGBCNFB","schema_version":"1.0","canonical_sha256":"0e0c1134a1e2508fcd7a8afb560f9f0e3775154ec51c4a5fc49339fc3ea21f17","source":{"kind":"arxiv","id":"1701.04079","version":1},"attestation_state":"computed","paper":{"title":"Agent-Agnostic Human-in-the-Loop Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andreas Stuhlm\\\"uller, David Abel, John Salvatier, Owain Evans","submitted_at":"2017-01-15T17:14:40Z","abstract_excerpt":"Providing Reinforcement Learning agents with expert advice can dramatically improve various aspects of learning. Prior work has developed teaching protocols that enable agents to learn efficiently in complex environments; many of these methods tailor the teacher's guidance to agents with a particular representation or underlying learning scheme, offering effective but specialized teaching procedures. In this work, we explore protocol programs, an agent-agnostic schema for Human-in-the-Loop Reinforcement Learning. Our goal is to incorporate the beneficial properties of a human teacher into Rein"},"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":"1701.04079","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-01-15T17:14:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ec2668c119b1c48653ae1124e7e6498f8738cb192bedf3ec6a41a30835fb9619","abstract_canon_sha256":"7fcc84b5f5fec88a85045816fbd7eb66f954616e58e48131052d9ca564fdbb1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:47.904981Z","signature_b64":"pKnA6IgtyptR1FWUaNcpQLUHQe67BSWbJhGsrLTCGGV0mAUuz4b8P40/Su1YyEq8pzHznsn/ZSeGI/2TyhemDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e0c1134a1e2508fcd7a8afb560f9f0e3775154ec51c4a5fc49339fc3ea21f17","last_reissued_at":"2026-05-18T00:52:47.904348Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:47.904348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Agent-Agnostic Human-in-the-Loop Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andreas Stuhlm\\\"uller, David Abel, John Salvatier, Owain Evans","submitted_at":"2017-01-15T17:14:40Z","abstract_excerpt":"Providing Reinforcement Learning agents with expert advice can dramatically improve various aspects of learning. Prior work has developed teaching protocols that enable agents to learn efficiently in complex environments; many of these methods tailor the teacher's guidance to agents with a particular representation or underlying learning scheme, offering effective but specialized teaching procedures. In this work, we explore protocol programs, an agent-agnostic schema for Human-in-the-Loop Reinforcement Learning. Our goal is to incorporate the beneficial properties of a human teacher into Rein"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.04079","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":"1701.04079","created_at":"2026-05-18T00:52:47.904447+00:00"},{"alias_kind":"arxiv_version","alias_value":"1701.04079v1","created_at":"2026-05-18T00:52:47.904447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.04079","created_at":"2026-05-18T00:52:47.904447+00:00"},{"alias_kind":"pith_short_12","alias_value":"BYGBCNFB4JII","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"BYGBCNFB4JII7TL2","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"BYGBCNFB","created_at":"2026-05-18T12:31:08.081275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14723","citing_title":"Bounded Autonomy for Enterprise AI: Typed Action Contracts and Consumer-Side Execution","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BYGBCNFB4JII7TL2RL5VMD47BY","json":"https://pith.science/pith/BYGBCNFB4JII7TL2RL5VMD47BY.json","graph_json":"https://pith.science/api/pith-number/BYGBCNFB4JII7TL2RL5VMD47BY/graph.json","events_json":"https://pith.science/api/pith-number/BYGBCNFB4JII7TL2RL5VMD47BY/events.json","paper":"https://pith.science/paper/BYGBCNFB"},"agent_actions":{"view_html":"https://pith.science/pith/BYGBCNFB4JII7TL2RL5VMD47BY","download_json":"https://pith.science/pith/BYGBCNFB4JII7TL2RL5VMD47BY.json","view_paper":"https://pith.science/paper/BYGBCNFB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1701.04079&json=true","fetch_graph":"https://pith.science/api/pith-number/BYGBCNFB4JII7TL2RL5VMD47BY/graph.json","fetch_events":"https://pith.science/api/pith-number/BYGBCNFB4JII7TL2RL5VMD47BY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BYGBCNFB4JII7TL2RL5VMD47BY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BYGBCNFB4JII7TL2RL5VMD47BY/action/storage_attestation","attest_author":"https://pith.science/pith/BYGBCNFB4JII7TL2RL5VMD47BY/action/author_attestation","sign_citation":"https://pith.science/pith/BYGBCNFB4JII7TL2RL5VMD47BY/action/citation_signature","submit_replication":"https://pith.science/pith/BYGBCNFB4JII7TL2RL5VMD47BY/action/replication_record"}},"created_at":"2026-05-18T00:52:47.904447+00:00","updated_at":"2026-05-18T00:52:47.904447+00:00"}