{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:BYGBCNFB4JII7TL2RL5VMD47BY","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":"7fcc84b5f5fec88a85045816fbd7eb66f954616e58e48131052d9ca564fdbb1d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-01-15T17:14:40Z","title_canon_sha256":"ec2668c119b1c48653ae1124e7e6498f8738cb192bedf3ec6a41a30835fb9619"},"schema_version":"1.0","source":{"id":"1701.04079","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.04079","created_at":"2026-05-18T00:52:47Z"},{"alias_kind":"arxiv_version","alias_value":"1701.04079v1","created_at":"2026-05-18T00:52:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.04079","created_at":"2026-05-18T00:52:47Z"},{"alias_kind":"pith_short_12","alias_value":"BYGBCNFB4JII","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BYGBCNFB4JII7TL2","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BYGBCNFB","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:a000fcd525b4693a526e18e4a2861a887344f1c1f4e8fbf603d7796b33070689","target":"graph","created_at":"2026-05-18T00:52:47Z","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":"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","authors_text":"Andreas Stuhlm\\\"uller, David Abel, John Salvatier, Owain Evans","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-01-15T17:14:40Z","title":"Agent-Agnostic Human-in-the-Loop Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.04079","kind":"arxiv","version":1},"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:f3cfd5d0e99be315446cea153c834aacd6d9d688df4fceff8f752d2ce6fe6489","target":"record","created_at":"2026-05-18T00:52:47Z","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":"7fcc84b5f5fec88a85045816fbd7eb66f954616e58e48131052d9ca564fdbb1d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-01-15T17:14:40Z","title_canon_sha256":"ec2668c119b1c48653ae1124e7e6498f8738cb192bedf3ec6a41a30835fb9619"},"schema_version":"1.0","source":{"id":"1701.04079","kind":"arxiv","version":1}},"canonical_sha256":"0e0c1134a1e2508fcd7a8afb560f9f0e3775154ec51c4a5fc49339fc3ea21f17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e0c1134a1e2508fcd7a8afb560f9f0e3775154ec51c4a5fc49339fc3ea21f17","first_computed_at":"2026-05-18T00:52:47.904348Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:52:47.904348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pKnA6IgtyptR1FWUaNcpQLUHQe67BSWbJhGsrLTCGGV0mAUuz4b8P40/Su1YyEq8pzHznsn/ZSeGI/2TyhemDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:52:47.904981Z","signed_message":"canonical_sha256_bytes"},"source_id":"1701.04079","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3cfd5d0e99be315446cea153c834aacd6d9d688df4fceff8f752d2ce6fe6489","sha256:a000fcd525b4693a526e18e4a2861a887344f1c1f4e8fbf603d7796b33070689"],"state_sha256":"1db7aeea831ca4b8628e6e279504b591e4680e07ba50888b3bfe1bed995333c2"}