{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UST4TBA75M5BNCVN5NG7RBO3JC","short_pith_number":"pith:UST4TBA7","schema_version":"1.0","canonical_sha256":"a4a7c9841feb3a168aadeb4df885db48abc48b96903836e2013df03461609495","source":{"kind":"arxiv","id":"2305.13741","version":1},"attestation_state":"computed","paper":{"title":"L-SA: Learning Under-Explored Targets in Multi-Target Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Byoung-Tak Zhang, Hyundo Lee, Kibeom Kim, Minsu Lee, Min Whoo Lee, Moonheon Lee","submitted_at":"2023-05-23T06:51:51Z","abstract_excerpt":"Tasks that involve interaction with various targets are called multi-target tasks. When applying general reinforcement learning approaches for such tasks, certain targets that are difficult to access or interact with may be neglected throughout the course of training - a predicament we call Under-explored Target Problem (UTP). To address this problem, we propose L-SA (Learning by adaptive Sampling and Active querying) framework that includes adaptive sampling and active querying. In the L-SA framework, adaptive sampling dynamically samples targets with the highest increase of success rates at "},"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":"2305.13741","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T06:51:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bfe491c2b711527fdaf44af58c357339a5f1e5894be2405c1db0ef98f8668ccb","abstract_canon_sha256":"015aab8ef4e532bd0f40c83e53acb5d4dfc3f5770e473c340088b3df5bf29671"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:56.952379Z","signature_b64":"wnahqITfiRavAUe8JZUw6H5WWYYQi5WFVHtsc1hO1BuOSPvxf/6npVS6POWI2ZiPyRrfD95PIrPQDzu2uGR4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4a7c9841feb3a168aadeb4df885db48abc48b96903836e2013df03461609495","last_reissued_at":"2026-07-05T06:12:56.951911Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:56.951911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"L-SA: Learning Under-Explored Targets in Multi-Target Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Byoung-Tak Zhang, Hyundo Lee, Kibeom Kim, Minsu Lee, Min Whoo Lee, Moonheon Lee","submitted_at":"2023-05-23T06:51:51Z","abstract_excerpt":"Tasks that involve interaction with various targets are called multi-target tasks. When applying general reinforcement learning approaches for such tasks, certain targets that are difficult to access or interact with may be neglected throughout the course of training - a predicament we call Under-explored Target Problem (UTP). To address this problem, we propose L-SA (Learning by adaptive Sampling and Active querying) framework that includes adaptive sampling and active querying. In the L-SA framework, adaptive sampling dynamically samples targets with the highest increase of success rates at "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13741","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/2305.13741/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":"2305.13741","created_at":"2026-07-05T06:12:56.951973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13741v1","created_at":"2026-07-05T06:12:56.951973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13741","created_at":"2026-07-05T06:12:56.951973+00:00"},{"alias_kind":"pith_short_12","alias_value":"UST4TBA75M5B","created_at":"2026-07-05T06:12:56.951973+00:00"},{"alias_kind":"pith_short_16","alias_value":"UST4TBA75M5BNCVN","created_at":"2026-07-05T06:12:56.951973+00:00"},{"alias_kind":"pith_short_8","alias_value":"UST4TBA7","created_at":"2026-07-05T06:12:56.951973+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.17842","citing_title":"From Sparse to Dense: Toddler-inspired Reward Transition in Goal-Oriented Reinforcement Learning","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UST4TBA75M5BNCVN5NG7RBO3JC","json":"https://pith.science/pith/UST4TBA75M5BNCVN5NG7RBO3JC.json","graph_json":"https://pith.science/api/pith-number/UST4TBA75M5BNCVN5NG7RBO3JC/graph.json","events_json":"https://pith.science/api/pith-number/UST4TBA75M5BNCVN5NG7RBO3JC/events.json","paper":"https://pith.science/paper/UST4TBA7"},"agent_actions":{"view_html":"https://pith.science/pith/UST4TBA75M5BNCVN5NG7RBO3JC","download_json":"https://pith.science/pith/UST4TBA75M5BNCVN5NG7RBO3JC.json","view_paper":"https://pith.science/paper/UST4TBA7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13741&json=true","fetch_graph":"https://pith.science/api/pith-number/UST4TBA75M5BNCVN5NG7RBO3JC/graph.json","fetch_events":"https://pith.science/api/pith-number/UST4TBA75M5BNCVN5NG7RBO3JC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UST4TBA75M5BNCVN5NG7RBO3JC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UST4TBA75M5BNCVN5NG7RBO3JC/action/storage_attestation","attest_author":"https://pith.science/pith/UST4TBA75M5BNCVN5NG7RBO3JC/action/author_attestation","sign_citation":"https://pith.science/pith/UST4TBA75M5BNCVN5NG7RBO3JC/action/citation_signature","submit_replication":"https://pith.science/pith/UST4TBA75M5BNCVN5NG7RBO3JC/action/replication_record"}},"created_at":"2026-07-05T06:12:56.951973+00:00","updated_at":"2026-07-05T06:12:56.951973+00:00"}