{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:J6CDMV7QICQGF4XVY5ZQAXEK62","short_pith_number":"pith:J6CDMV7Q","schema_version":"1.0","canonical_sha256":"4f843657f040a062f2f5c773005c8af6ad2494c9c72f148d8607df956c66a1d7","source":{"kind":"arxiv","id":"2210.05187","version":1},"attestation_state":"computed","paper":{"title":"Broad-persistent Advice for Interactive Reinforcement Learning Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Adam Bignold, Francisco Cruz, Hung Son Nguyen, Peter Vamplew, Richard Dazeley","submitted_at":"2022-10-11T06:46:27Z","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"},"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":"2210.05187","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-10-11T06:46:27Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"8b4c9a98d17a16ff6ed093f4a92b27df1706ad5edf9b6eb2e785a483b8327f26","abstract_canon_sha256":"8222191e2722a762f8ee3c7a686209d4cad62a72caa5d17c724136ded478d110"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:13.924116Z","signature_b64":"UYsKSXhm1kGeezCGgsHe3c4gNL00J25wZsKGLd4jl6Nf7YRqxxXMXe8NPJ3QtWtaMkiVyc9vJq1t9ahfvwojCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f843657f040a062f2f5c773005c8af6ad2494c9c72f148d8607df956c66a1d7","last_reissued_at":"2026-07-05T05:05:13.923608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:13.923608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Broad-persistent Advice for Interactive Reinforcement Learning Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Adam Bignold, Francisco Cruz, Hung Son Nguyen, Peter Vamplew, Richard Dazeley","submitted_at":"2022-10-11T06:46:27Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05187","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.05187/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2210.05187","created_at":"2026-07-05T05:05:13.923680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.05187v1","created_at":"2026-07-05T05:05:13.923680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05187","created_at":"2026-07-05T05:05:13.923680+00:00"},{"alias_kind":"pith_short_12","alias_value":"J6CDMV7QICQG","created_at":"2026-07-05T05:05:13.923680+00:00"},{"alias_kind":"pith_short_16","alias_value":"J6CDMV7QICQGF4XV","created_at":"2026-07-05T05:05:13.923680+00:00"},{"alias_kind":"pith_short_8","alias_value":"J6CDMV7Q","created_at":"2026-07-05T05:05:13.923680+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.11761","citing_title":"Mapping out the Space of Human Feedback for Reinforcement Learning: A Conceptual Framework","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J6CDMV7QICQGF4XVY5ZQAXEK62","json":"https://pith.science/pith/J6CDMV7QICQGF4XVY5ZQAXEK62.json","graph_json":"https://pith.science/api/pith-number/J6CDMV7QICQGF4XVY5ZQAXEK62/graph.json","events_json":"https://pith.science/api/pith-number/J6CDMV7QICQGF4XVY5ZQAXEK62/events.json","paper":"https://pith.science/paper/J6CDMV7Q"},"agent_actions":{"view_html":"https://pith.science/pith/J6CDMV7QICQGF4XVY5ZQAXEK62","download_json":"https://pith.science/pith/J6CDMV7QICQGF4XVY5ZQAXEK62.json","view_paper":"https://pith.science/paper/J6CDMV7Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.05187&json=true","fetch_graph":"https://pith.science/api/pith-number/J6CDMV7QICQGF4XVY5ZQAXEK62/graph.json","fetch_events":"https://pith.science/api/pith-number/J6CDMV7QICQGF4XVY5ZQAXEK62/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J6CDMV7QICQGF4XVY5ZQAXEK62/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J6CDMV7QICQGF4XVY5ZQAXEK62/action/storage_attestation","attest_author":"https://pith.science/pith/J6CDMV7QICQGF4XVY5ZQAXEK62/action/author_attestation","sign_citation":"https://pith.science/pith/J6CDMV7QICQGF4XVY5ZQAXEK62/action/citation_signature","submit_replication":"https://pith.science/pith/J6CDMV7QICQGF4XVY5ZQAXEK62/action/replication_record"}},"created_at":"2026-07-05T05:05:13.923680+00:00","updated_at":"2026-07-05T05:05:13.923680+00:00"}