{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B2F2ULYCSVUFTY45C7HWAXPI5G","short_pith_number":"pith:B2F2ULYC","schema_version":"1.0","canonical_sha256":"0e8baa2f02956859e39d17cf605de8e998313d6ac440c47135689883d45e466b","source":{"kind":"arxiv","id":"2402.03771","version":3},"attestation_state":"computed","paper":{"title":"Reinforcement Learning from Bagged Reward","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Guoqing Liu, Masashi Sugiyama, Qiyu Wu, Xin-Qiang Cai, Yao-Xiang Ding, Yuting Tang","submitted_at":"2024-02-06T07:26:44Z","abstract_excerpt":"In Reinforcement Learning (RL), it is commonly assumed that an immediate reward signal is generated for each action taken by the agent, helping the agent maximize cumulative rewards to obtain the optimal policy. However, in many real-world scenarios, designing immediate reward signals is difficult; instead, agents receive a single reward that is contingent upon a partial sequence or a complete trajectory. In this work, we define this challenging problem as RL from Bagged Reward (RLBR), where sequences of data are treated as bags with non-Markovian bagged rewards, leading to the formulation of "},"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":"2402.03771","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T07:26:44Z","cross_cats_sorted":[],"title_canon_sha256":"aa5d10bb4b412f53c1c69deb4628be7c2d6c031816e7b499966567431c4da326","abstract_canon_sha256":"89b84fe7a1f7ea0b77f018cf6904f81699473f3e29d4b16d5aaa1dab1b2fc85a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:24.105706Z","signature_b64":"9ZOTj3KBlzcLGoCNCcnYaygekG06yBlc7fAOZKQlI0cpfqaj7ERlgzn6oVI8Kxd9l3X+h6WPp5yOmNGrEBc8Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e8baa2f02956859e39d17cf605de8e998313d6ac440c47135689883d45e466b","last_reissued_at":"2026-07-05T09:26:24.105292Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:24.105292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning from Bagged Reward","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Guoqing Liu, Masashi Sugiyama, Qiyu Wu, Xin-Qiang Cai, Yao-Xiang Ding, Yuting Tang","submitted_at":"2024-02-06T07:26:44Z","abstract_excerpt":"In Reinforcement Learning (RL), it is commonly assumed that an immediate reward signal is generated for each action taken by the agent, helping the agent maximize cumulative rewards to obtain the optimal policy. However, in many real-world scenarios, designing immediate reward signals is difficult; instead, agents receive a single reward that is contingent upon a partial sequence or a complete trajectory. In this work, we define this challenging problem as RL from Bagged Reward (RLBR), where sequences of data are treated as bags with non-Markovian bagged rewards, leading to the formulation of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03771","kind":"arxiv","version":3},"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/2402.03771/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":"2402.03771","created_at":"2026-07-05T09:26:24.105356+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03771v3","created_at":"2026-07-05T09:26:24.105356+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03771","created_at":"2026-07-05T09:26:24.105356+00:00"},{"alias_kind":"pith_short_12","alias_value":"B2F2ULYCSVUF","created_at":"2026-07-05T09:26:24.105356+00:00"},{"alias_kind":"pith_short_16","alias_value":"B2F2ULYCSVUFTY45","created_at":"2026-07-05T09:26:24.105356+00:00"},{"alias_kind":"pith_short_8","alias_value":"B2F2ULYC","created_at":"2026-07-05T09:26:24.105356+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/B2F2ULYCSVUFTY45C7HWAXPI5G","json":"https://pith.science/pith/B2F2ULYCSVUFTY45C7HWAXPI5G.json","graph_json":"https://pith.science/api/pith-number/B2F2ULYCSVUFTY45C7HWAXPI5G/graph.json","events_json":"https://pith.science/api/pith-number/B2F2ULYCSVUFTY45C7HWAXPI5G/events.json","paper":"https://pith.science/paper/B2F2ULYC"},"agent_actions":{"view_html":"https://pith.science/pith/B2F2ULYCSVUFTY45C7HWAXPI5G","download_json":"https://pith.science/pith/B2F2ULYCSVUFTY45C7HWAXPI5G.json","view_paper":"https://pith.science/paper/B2F2ULYC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03771&json=true","fetch_graph":"https://pith.science/api/pith-number/B2F2ULYCSVUFTY45C7HWAXPI5G/graph.json","fetch_events":"https://pith.science/api/pith-number/B2F2ULYCSVUFTY45C7HWAXPI5G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B2F2ULYCSVUFTY45C7HWAXPI5G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B2F2ULYCSVUFTY45C7HWAXPI5G/action/storage_attestation","attest_author":"https://pith.science/pith/B2F2ULYCSVUFTY45C7HWAXPI5G/action/author_attestation","sign_citation":"https://pith.science/pith/B2F2ULYCSVUFTY45C7HWAXPI5G/action/citation_signature","submit_replication":"https://pith.science/pith/B2F2ULYCSVUFTY45C7HWAXPI5G/action/replication_record"}},"created_at":"2026-07-05T09:26:24.105356+00:00","updated_at":"2026-07-05T09:26:24.105356+00:00"}