{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:AQ6N7J3ZPYBNLGVWZNEEYBIYCC","short_pith_number":"pith:AQ6N7J3Z","canonical_record":{"source":{"id":"2202.06450","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-14T01:31:46Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"9dfe66374953825583ff5c2f274890f506b0a5aa5eb9c6b8b72db1a00293b0f4","abstract_canon_sha256":"8a29646179ad717f3278f10785896ed78e09c47bacd14a3cbc50eca95726f72f"},"schema_version":"1.0"},"canonical_sha256":"043cdfa7797e02d59ab6cb484c051810bd4265740644e86ae06a7f3ac26b1d45","source":{"kind":"arxiv","id":"2202.06450","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:AQ6N7J3ZPYBNLGVWZNEEYBIYCC","target":"record","payload":{"canonical_record":{"source":{"id":"2202.06450","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-14T01:31:46Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"9dfe66374953825583ff5c2f274890f506b0a5aa5eb9c6b8b72db1a00293b0f4","abstract_canon_sha256":"8a29646179ad717f3278f10785896ed78e09c47bacd14a3cbc50eca95726f72f"},"schema_version":"1.0"},"canonical_sha256":"043cdfa7797e02d59ab6cb484c051810bd4265740644e86ae06a7f3ac26b1d45","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:53:26.902373Z","signature_b64":"Im9ojdT1qz/73PoTs7gfNp3LyviV/PdnPzDrFEBBhMNzBz8jaBl0M908sx0QA0+mD2ixHhtdA9/rmIx6ivaGCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"043cdfa7797e02d59ab6cb484c051810bd4265740644e86ae06a7f3ac26b1d45","last_reissued_at":"2026-07-05T04:53:26.901835Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:53:26.901835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.06450","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:53:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C7nZPkSDuSGkqls+b6by+2yMQ6CwMopAmbZCTvladZXxAzsOdUq1tJxyRSjgH4Ik6pSUnxX1x4bE1IVZg43QCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:12:37.427147Z"},"content_sha256":"c557121de0423c77748701569d7f42acac32d37bf8404fc18f465c39bde96cbf","schema_version":"1.0","event_id":"sha256:c557121de0423c77748701569d7f42acac32d37bf8404fc18f465c39bde96cbf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:AQ6N7J3ZPYBNLGVWZNEEYBIYCC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiawei Huang, Jinglin Chen, Li Zhao, Nan Jiang, Tao Qin, Tie-Yan Liu","submitted_at":"2022-02-14T01:31:46Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.06450","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/2202.06450/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:53:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gj2lQw4NFS12Fd1/yGaMCXWEHUztmTR1/nVK2CKOi6/7eJTM0PkjtmVkhNTsRU9pEw4wBInxDt6IMxAylO32DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:12:37.427777Z"},"content_sha256":"abe711a3a99b487cd059986bc8df7447769e63c52ce0067db42f213a6df75c6c","schema_version":"1.0","event_id":"sha256:abe711a3a99b487cd059986bc8df7447769e63c52ce0067db42f213a6df75c6c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AQ6N7J3ZPYBNLGVWZNEEYBIYCC/bundle.json","state_url":"https://pith.science/pith/AQ6N7J3ZPYBNLGVWZNEEYBIYCC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AQ6N7J3ZPYBNLGVWZNEEYBIYCC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T03:12:37Z","links":{"resolver":"https://pith.science/pith/AQ6N7J3ZPYBNLGVWZNEEYBIYCC","bundle":"https://pith.science/pith/AQ6N7J3ZPYBNLGVWZNEEYBIYCC/bundle.json","state":"https://pith.science/pith/AQ6N7J3ZPYBNLGVWZNEEYBIYCC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AQ6N7J3ZPYBNLGVWZNEEYBIYCC/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b3e8D+mM2K1RztKMP+glEotDsP6Q/Hs/HGSP5LF9+vbrMFNB7yvaGit++v4vLn1sb1W3dF9YKsx0WvnnqHzdBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T03:12:37.432685Z","bundle_sha256":"9a175db87cd0692ca534c682e6149fa64dc332504889fd8c4019587ae92192a1"}}