{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:J6CDMV7QICQGF4XVY5ZQAXEK62","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":"8222191e2722a762f8ee3c7a686209d4cad62a72caa5d17c724136ded478d110","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-10-11T06:46:27Z","title_canon_sha256":"8b4c9a98d17a16ff6ed093f4a92b27df1706ad5edf9b6eb2e785a483b8327f26"},"schema_version":"1.0","source":{"id":"2210.05187","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05187","created_at":"2026-07-05T05:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05187v1","created_at":"2026-07-05T05:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05187","created_at":"2026-07-05T05:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"J6CDMV7QICQG","created_at":"2026-07-05T05:05:13Z"},{"alias_kind":"pith_short_16","alias_value":"J6CDMV7QICQGF4XV","created_at":"2026-07-05T05:05:13Z"},{"alias_kind":"pith_short_8","alias_value":"J6CDMV7Q","created_at":"2026-07-05T05:05:13Z"}],"graph_snapshots":[{"event_id":"sha256:ccfc2f0950d2ff8e17589f6aad52c46bc5f3e49773721df40de5fd77e578e078","target":"graph","created_at":"2026-07-05T05:05:13Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2210.05187/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The use of interactive advice in reinforcement learning scenarios allows for speeding up the learning process for autonomous agents. Current interactive reinforcement learning research has been limited to real-time interactions that offer relevant user advice to the current state only. Moreover, the information provided by each interaction is not retained and instead discarded by the agent after a single use. In this paper, we present a method for retaining and reusing provided knowledge, allowing trainers to give general advice relevant to more than just the current state. Results obtained sh","authors_text":"Adam Bignold, Francisco Cruz, Hung Son Nguyen, Peter Vamplew, Richard Dazeley","cross_cats":["cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-10-11T06:46:27Z","title":"Broad-persistent Advice for Interactive Reinforcement Learning Scenarios"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05187","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":"sha256:208a34eb4b1ba7b0a2dcfec4ed6f8077ff04635d179bb41f4396926e68cb1d57","target":"record","created_at":"2026-07-05T05:05:13Z","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":"8222191e2722a762f8ee3c7a686209d4cad62a72caa5d17c724136ded478d110","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-10-11T06:46:27Z","title_canon_sha256":"8b4c9a98d17a16ff6ed093f4a92b27df1706ad5edf9b6eb2e785a483b8327f26"},"schema_version":"1.0","source":{"id":"2210.05187","kind":"arxiv","version":1}},"canonical_sha256":"4f843657f040a062f2f5c773005c8af6ad2494c9c72f148d8607df956c66a1d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f843657f040a062f2f5c773005c8af6ad2494c9c72f148d8607df956c66a1d7","first_computed_at":"2026-07-05T05:05:13.923608Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:05:13.923608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UYsKSXhm1kGeezCGgsHe3c4gNL00J25wZsKGLd4jl6Nf7YRqxxXMXe8NPJ3QtWtaMkiVyc9vJq1t9ahfvwojCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:05:13.924116Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.05187","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:208a34eb4b1ba7b0a2dcfec4ed6f8077ff04635d179bb41f4396926e68cb1d57","sha256:ccfc2f0950d2ff8e17589f6aad52c46bc5f3e49773721df40de5fd77e578e078"],"state_sha256":"e2de9cf68c5fd21f93d5b84bf92fe3b421b1246199e94b02c0712ea2fc31823f"}