{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:6U7M2QBX3WYVGCBQ35Q77AX73N","short_pith_number":"pith:6U7M2QBX","schema_version":"1.0","canonical_sha256":"f53ecd4037ddb1530830df61ff82ffdb7bcf444f1c4b90bee829ff7816b01692","source":{"kind":"arxiv","id":"1512.01124","version":2},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning with Attention for Slate Markov Decision Processes with High-Dimensional States and Actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.LG"],"primary_cat":"cs.AI","authors_text":"Ben Coppin, Daniel Visentin, Gabriel Dulac-Arnold, Peter Sunehag, Richard Evans, Yori Zwols","submitted_at":"2015-12-03T15:51:30Z","abstract_excerpt":"Many real-world problems come with action spaces represented as feature vectors. Although high-dimensional control is a largely unsolved problem, there has recently been progress for modest dimensionalities. Here we report on a successful attempt at addressing problems of dimensionality as high as $2000$, of a particular form. Motivated by important applications such as recommendation systems that do not fit the standard reinforcement learning frameworks, we introduce Slate Markov Decision Processes (slate-MDPs). A Slate-MDP is an MDP with a combinatorial action space consisting of slates (tup"},"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":"1512.01124","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-12-03T15:51:30Z","cross_cats_sorted":["cs.HC","cs.LG"],"title_canon_sha256":"d1d5e977d92bfe509a7b9ceb33f9e119be059eaa292650bf652b974df5a69999","abstract_canon_sha256":"5bd4e9e1e299ecc7a383815c4f55b9050c5b5d0211a8f8c91845c526d2da64b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:24:14.061303Z","signature_b64":"qdABkhr8wlvZBCm9U5pysVyThAnnItvA6Uf2yu0C14EqkDEtzktqe+FdgGNfGNWH9Sf8MInG2ZTh/LJeAF4hCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f53ecd4037ddb1530830df61ff82ffdb7bcf444f1c4b90bee829ff7816b01692","last_reissued_at":"2026-05-18T01:24:14.060663Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:24:14.060663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning with Attention for Slate Markov Decision Processes with High-Dimensional States and Actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.LG"],"primary_cat":"cs.AI","authors_text":"Ben Coppin, Daniel Visentin, Gabriel Dulac-Arnold, Peter Sunehag, Richard Evans, Yori Zwols","submitted_at":"2015-12-03T15:51:30Z","abstract_excerpt":"Many real-world problems come with action spaces represented as feature vectors. Although high-dimensional control is a largely unsolved problem, there has recently been progress for modest dimensionalities. Here we report on a successful attempt at addressing problems of dimensionality as high as $2000$, of a particular form. Motivated by important applications such as recommendation systems that do not fit the standard reinforcement learning frameworks, we introduce Slate Markov Decision Processes (slate-MDPs). A Slate-MDP is an MDP with a combinatorial action space consisting of slates (tup"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.01124","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1512.01124","created_at":"2026-05-18T01:24:14.060770+00:00"},{"alias_kind":"arxiv_version","alias_value":"1512.01124v2","created_at":"2026-05-18T01:24:14.060770+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.01124","created_at":"2026-05-18T01:24:14.060770+00:00"},{"alias_kind":"pith_short_12","alias_value":"6U7M2QBX3WYV","created_at":"2026-05-18T12:29:07.941421+00:00"},{"alias_kind":"pith_short_16","alias_value":"6U7M2QBX3WYVGCBQ","created_at":"2026-05-18T12:29:07.941421+00:00"},{"alias_kind":"pith_short_8","alias_value":"6U7M2QBX","created_at":"2026-05-18T12:29:07.941421+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2512.13726","citing_title":"Time-Constrained Recommendations: Reinforcement Learning Strategies for E-Commerce","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6U7M2QBX3WYVGCBQ35Q77AX73N","json":"https://pith.science/pith/6U7M2QBX3WYVGCBQ35Q77AX73N.json","graph_json":"https://pith.science/api/pith-number/6U7M2QBX3WYVGCBQ35Q77AX73N/graph.json","events_json":"https://pith.science/api/pith-number/6U7M2QBX3WYVGCBQ35Q77AX73N/events.json","paper":"https://pith.science/paper/6U7M2QBX"},"agent_actions":{"view_html":"https://pith.science/pith/6U7M2QBX3WYVGCBQ35Q77AX73N","download_json":"https://pith.science/pith/6U7M2QBX3WYVGCBQ35Q77AX73N.json","view_paper":"https://pith.science/paper/6U7M2QBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1512.01124&json=true","fetch_graph":"https://pith.science/api/pith-number/6U7M2QBX3WYVGCBQ35Q77AX73N/graph.json","fetch_events":"https://pith.science/api/pith-number/6U7M2QBX3WYVGCBQ35Q77AX73N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6U7M2QBX3WYVGCBQ35Q77AX73N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6U7M2QBX3WYVGCBQ35Q77AX73N/action/storage_attestation","attest_author":"https://pith.science/pith/6U7M2QBX3WYVGCBQ35Q77AX73N/action/author_attestation","sign_citation":"https://pith.science/pith/6U7M2QBX3WYVGCBQ35Q77AX73N/action/citation_signature","submit_replication":"https://pith.science/pith/6U7M2QBX3WYVGCBQ35Q77AX73N/action/replication_record"}},"created_at":"2026-05-18T01:24:14.060770+00:00","updated_at":"2026-05-18T01:24:14.060770+00:00"}