{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4V5XKODINU5XMOETSPZFYRQ2KA","short_pith_number":"pith:4V5XKODI","schema_version":"1.0","canonical_sha256":"e57b7538686d3b76389393f25c461a501d6074a25c7ac144ab3a3e1cb88db3fa","source":{"kind":"arxiv","id":"1909.03638","version":1},"attestation_state":"computed","paper":{"title":"Solving Continual Combinatorial Selection via Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Donggyu Yun, Hai H. Tran, Hyeryung Jang, Hyoju Chung, HyungSeok Song, Kyunghwan Son, Se-eun Yoon, Yung Yi","submitted_at":"2019-09-09T05:45:11Z","abstract_excerpt":"We consider the Markov Decision Process (MDP) of selecting a subset of items at each step, termed the Select-MDP (S-MDP). The large state and action spaces of S-MDPs make them intractable to solve with typical reinforcement learning (RL) algorithms especially when the number of items is huge. In this paper, we present a deep RL algorithm to solve this issue by adopting the following key ideas. First, we convert the original S-MDP into an Iterative Select-MDP (IS-MDP), which is equivalent to the S-MDP in terms of optimal actions. IS-MDP decomposes a joint action of selecting K items simultaneou"},"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":"1909.03638","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-09T05:45:11Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"afd64279dfafbba19e8328c94d33ff315df2aa49616f284bb2b5e1e6d6a56f62","abstract_canon_sha256":"296b5663aea7a39711ad4d196b2309a46def4b6883c7c2abbf84d8be06c480d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:03:07.607063Z","signature_b64":"y5Fmb71jrZEf3rSpaAr4EPdc5emi+yfw6RZXDLJaCOicozPn3gHUt8ZXNCtpS8gKEqwEhyVHJrZfAr0s/rI7Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e57b7538686d3b76389393f25c461a501d6074a25c7ac144ab3a3e1cb88db3fa","last_reissued_at":"2026-07-05T00:03:07.606564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:03:07.606564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solving Continual Combinatorial Selection via Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Donggyu Yun, Hai H. Tran, Hyeryung Jang, Hyoju Chung, HyungSeok Song, Kyunghwan Son, Se-eun Yoon, Yung Yi","submitted_at":"2019-09-09T05:45:11Z","abstract_excerpt":"We consider the Markov Decision Process (MDP) of selecting a subset of items at each step, termed the Select-MDP (S-MDP). The large state and action spaces of S-MDPs make them intractable to solve with typical reinforcement learning (RL) algorithms especially when the number of items is huge. In this paper, we present a deep RL algorithm to solve this issue by adopting the following key ideas. First, we convert the original S-MDP into an Iterative Select-MDP (IS-MDP), which is equivalent to the S-MDP in terms of optimal actions. IS-MDP decomposes a joint action of selecting K items simultaneou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.03638","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/1909.03638/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":"1909.03638","created_at":"2026-07-05T00:03:07.606621+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.03638v1","created_at":"2026-07-05T00:03:07.606621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.03638","created_at":"2026-07-05T00:03:07.606621+00:00"},{"alias_kind":"pith_short_12","alias_value":"4V5XKODINU5X","created_at":"2026-07-05T00:03:07.606621+00:00"},{"alias_kind":"pith_short_16","alias_value":"4V5XKODINU5XMOET","created_at":"2026-07-05T00:03:07.606621+00:00"},{"alias_kind":"pith_short_8","alias_value":"4V5XKODI","created_at":"2026-07-05T00:03:07.606621+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/4V5XKODINU5XMOETSPZFYRQ2KA","json":"https://pith.science/pith/4V5XKODINU5XMOETSPZFYRQ2KA.json","graph_json":"https://pith.science/api/pith-number/4V5XKODINU5XMOETSPZFYRQ2KA/graph.json","events_json":"https://pith.science/api/pith-number/4V5XKODINU5XMOETSPZFYRQ2KA/events.json","paper":"https://pith.science/paper/4V5XKODI"},"agent_actions":{"view_html":"https://pith.science/pith/4V5XKODINU5XMOETSPZFYRQ2KA","download_json":"https://pith.science/pith/4V5XKODINU5XMOETSPZFYRQ2KA.json","view_paper":"https://pith.science/paper/4V5XKODI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.03638&json=true","fetch_graph":"https://pith.science/api/pith-number/4V5XKODINU5XMOETSPZFYRQ2KA/graph.json","fetch_events":"https://pith.science/api/pith-number/4V5XKODINU5XMOETSPZFYRQ2KA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4V5XKODINU5XMOETSPZFYRQ2KA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4V5XKODINU5XMOETSPZFYRQ2KA/action/storage_attestation","attest_author":"https://pith.science/pith/4V5XKODINU5XMOETSPZFYRQ2KA/action/author_attestation","sign_citation":"https://pith.science/pith/4V5XKODINU5XMOETSPZFYRQ2KA/action/citation_signature","submit_replication":"https://pith.science/pith/4V5XKODINU5XMOETSPZFYRQ2KA/action/replication_record"}},"created_at":"2026-07-05T00:03:07.606621+00:00","updated_at":"2026-07-05T00:03:07.606621+00:00"}