{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YHYBG6LJFZME7J3APHLBDOK5G2","short_pith_number":"pith:YHYBG6LJ","schema_version":"1.0","canonical_sha256":"c1f01379692e584fa76079d611b95d36aa31d88d21093e06ff7aae83e1ce9c40","source":{"kind":"arxiv","id":"2112.15221","version":1},"attestation_state":"computed","paper":{"title":"Constraint Sampling Reinforcement Learning: Incorporating Expertise For Faster Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"David Arbour, Emma Brunskill, Georgios Theocharous, Tong Mu","submitted_at":"2021-12-30T22:02:42Z","abstract_excerpt":"Online reinforcement learning (RL) algorithms are often difficult to deploy in complex human-facing applications as they may learn slowly and have poor early performance. To address this, we introduce a practical algorithm for incorporating human insight to speed learning. Our algorithm, Constraint Sampling Reinforcement Learning (CSRL), incorporates prior domain knowledge as constraints/restrictions on the RL policy. It takes in multiple potential policy constraints to maintain robustness to misspecification of individual constraints while leveraging helpful ones to learn quickly. Given a bas"},"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":"2112.15221","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-12-30T22:02:42Z","cross_cats_sorted":[],"title_canon_sha256":"e23dbf4d423b91c06431b91c6061dbb9efd8a8468754aa91009487322d3df244","abstract_canon_sha256":"a31730752b53afec99498c663fbed2400c5f78f5f2026879d8cbaf4485d2d87b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:44:37.685942Z","signature_b64":"u3C17Uhlqbuy4Y1N2nm2uGBsHaqOAp8QkRqKjAfOARJD8HaEBXEfmfnBT14Dqyk/MZJbDYWBU4d4ksZGCNGuDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1f01379692e584fa76079d611b95d36aa31d88d21093e06ff7aae83e1ce9c40","last_reissued_at":"2026-07-05T03:44:37.685568Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:44:37.685568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constraint Sampling Reinforcement Learning: Incorporating Expertise For Faster Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"David Arbour, Emma Brunskill, Georgios Theocharous, Tong Mu","submitted_at":"2021-12-30T22:02:42Z","abstract_excerpt":"Online reinforcement learning (RL) algorithms are often difficult to deploy in complex human-facing applications as they may learn slowly and have poor early performance. To address this, we introduce a practical algorithm for incorporating human insight to speed learning. Our algorithm, Constraint Sampling Reinforcement Learning (CSRL), incorporates prior domain knowledge as constraints/restrictions on the RL policy. It takes in multiple potential policy constraints to maintain robustness to misspecification of individual constraints while leveraging helpful ones to learn quickly. Given a bas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.15221","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/2112.15221/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":"2112.15221","created_at":"2026-07-05T03:44:37.685640+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.15221v1","created_at":"2026-07-05T03:44:37.685640+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.15221","created_at":"2026-07-05T03:44:37.685640+00:00"},{"alias_kind":"pith_short_12","alias_value":"YHYBG6LJFZME","created_at":"2026-07-05T03:44:37.685640+00:00"},{"alias_kind":"pith_short_16","alias_value":"YHYBG6LJFZME7J3A","created_at":"2026-07-05T03:44:37.685640+00:00"},{"alias_kind":"pith_short_8","alias_value":"YHYBG6LJ","created_at":"2026-07-05T03:44:37.685640+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YHYBG6LJFZME7J3APHLBDOK5G2","json":"https://pith.science/pith/YHYBG6LJFZME7J3APHLBDOK5G2.json","graph_json":"https://pith.science/api/pith-number/YHYBG6LJFZME7J3APHLBDOK5G2/graph.json","events_json":"https://pith.science/api/pith-number/YHYBG6LJFZME7J3APHLBDOK5G2/events.json","paper":"https://pith.science/paper/YHYBG6LJ"},"agent_actions":{"view_html":"https://pith.science/pith/YHYBG6LJFZME7J3APHLBDOK5G2","download_json":"https://pith.science/pith/YHYBG6LJFZME7J3APHLBDOK5G2.json","view_paper":"https://pith.science/paper/YHYBG6LJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.15221&json=true","fetch_graph":"https://pith.science/api/pith-number/YHYBG6LJFZME7J3APHLBDOK5G2/graph.json","fetch_events":"https://pith.science/api/pith-number/YHYBG6LJFZME7J3APHLBDOK5G2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YHYBG6LJFZME7J3APHLBDOK5G2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YHYBG6LJFZME7J3APHLBDOK5G2/action/storage_attestation","attest_author":"https://pith.science/pith/YHYBG6LJFZME7J3APHLBDOK5G2/action/author_attestation","sign_citation":"https://pith.science/pith/YHYBG6LJFZME7J3APHLBDOK5G2/action/citation_signature","submit_replication":"https://pith.science/pith/YHYBG6LJFZME7J3APHLBDOK5G2/action/replication_record"}},"created_at":"2026-07-05T03:44:37.685640+00:00","updated_at":"2026-07-05T03:44:37.685640+00:00"}