{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:AQ6N7J3ZPYBNLGVWZNEEYBIYCC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8a29646179ad717f3278f10785896ed78e09c47bacd14a3cbc50eca95726f72f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-14T01:31:46Z","title_canon_sha256":"9dfe66374953825583ff5c2f274890f506b0a5aa5eb9c6b8b72db1a00293b0f4"},"schema_version":"1.0","source":{"id":"2202.06450","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.06450","created_at":"2026-07-05T04:53:26Z"},{"alias_kind":"arxiv_version","alias_value":"2202.06450v3","created_at":"2026-07-05T04:53:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.06450","created_at":"2026-07-05T04:53:26Z"},{"alias_kind":"pith_short_12","alias_value":"AQ6N7J3ZPYBN","created_at":"2026-07-05T04:53:26Z"},{"alias_kind":"pith_short_16","alias_value":"AQ6N7J3ZPYBNLGVW","created_at":"2026-07-05T04:53:26Z"},{"alias_kind":"pith_short_8","alias_value":"AQ6N7J3Z","created_at":"2026-07-05T04:53:26Z"}],"graph_snapshots":[{"event_id":"sha256:abe711a3a99b487cd059986bc8df7447769e63c52ce0067db42f213a6df75c6c","target":"graph","created_at":"2026-07-05T04:53:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2202.06450/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deployment efficiency is an important criterion for many real-world applications of reinforcement learning (RL). Despite the community's increasing interest, there lacks a formal theoretical formulation for the problem. In this paper, we propose such a formulation for deployment-efficient RL (DE-RL) from an \"optimization with constraints\" perspective: we are interested in exploring an MDP and obtaining a near-optimal policy within minimal \\emph{deployment complexity}, whereas in each deployment the policy can sample a large batch of data. Using finite-horizon linear MDPs as a concrete structur","authors_text":"Jiawei Huang, Jinglin Chen, Li Zhao, Nan Jiang, Tao Qin, Tie-Yan Liu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-14T01:31:46Z","title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.06450","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c557121de0423c77748701569d7f42acac32d37bf8404fc18f465c39bde96cbf","target":"record","created_at":"2026-07-05T04:53:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8a29646179ad717f3278f10785896ed78e09c47bacd14a3cbc50eca95726f72f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-14T01:31:46Z","title_canon_sha256":"9dfe66374953825583ff5c2f274890f506b0a5aa5eb9c6b8b72db1a00293b0f4"},"schema_version":"1.0","source":{"id":"2202.06450","kind":"arxiv","version":3}},"canonical_sha256":"043cdfa7797e02d59ab6cb484c051810bd4265740644e86ae06a7f3ac26b1d45","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"043cdfa7797e02d59ab6cb484c051810bd4265740644e86ae06a7f3ac26b1d45","first_computed_at":"2026-07-05T04:53:26.901835Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:53:26.901835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Im9ojdT1qz/73PoTs7gfNp3LyviV/PdnPzDrFEBBhMNzBz8jaBl0M908sx0QA0+mD2ixHhtdA9/rmIx6ivaGCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:53:26.902373Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.06450","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c557121de0423c77748701569d7f42acac32d37bf8404fc18f465c39bde96cbf","sha256:abe711a3a99b487cd059986bc8df7447769e63c52ce0067db42f213a6df75c6c"],"state_sha256":"9c3ccba0c4c51fa1033735e0816efe3bace218461a98c177dc4d1a5b528c86f3"}