{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:AOG3T77FGVVQCMRFHOCO3GQ6N5","short_pith_number":"pith:AOG3T77F","canonical_record":{"source":{"id":"2305.18443","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-29T03:25:22Z","cross_cats_sorted":[],"title_canon_sha256":"7b0c80249f63b7f85d5a71d391674b2c0776953d2a0f300915b31bc834f8e996","abstract_canon_sha256":"dd887a1737749b08f7967c6b98f089b16009d8abf5cc7d1d377c4826d89c4eb7"},"schema_version":"1.0"},"canonical_sha256":"038db9ffe5356b0132253b84ed9a1e6f41819b8b25211161f9ca876247e5b65b","source":{"kind":"arxiv","id":"2305.18443","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18443","created_at":"2026-07-05T06:15:00Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18443v1","created_at":"2026-07-05T06:15:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18443","created_at":"2026-07-05T06:15:00Z"},{"alias_kind":"pith_short_12","alias_value":"AOG3T77FGVVQ","created_at":"2026-07-05T06:15:00Z"},{"alias_kind":"pith_short_16","alias_value":"AOG3T77FGVVQCMRF","created_at":"2026-07-05T06:15:00Z"},{"alias_kind":"pith_short_8","alias_value":"AOG3T77F","created_at":"2026-07-05T06:15:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:AOG3T77FGVVQCMRFHOCO3GQ6N5","target":"record","payload":{"canonical_record":{"source":{"id":"2305.18443","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-29T03:25:22Z","cross_cats_sorted":[],"title_canon_sha256":"7b0c80249f63b7f85d5a71d391674b2c0776953d2a0f300915b31bc834f8e996","abstract_canon_sha256":"dd887a1737749b08f7967c6b98f089b16009d8abf5cc7d1d377c4826d89c4eb7"},"schema_version":"1.0"},"canonical_sha256":"038db9ffe5356b0132253b84ed9a1e6f41819b8b25211161f9ca876247e5b65b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:00.981307Z","signature_b64":"5SQFrGWX8PsYmA+G4gfFwHc5t9sA58KII2dgSOUWQ3y+AgvJaSIZZZcvNbZGFx6HeFlg72t2XZMCSmOyNB3TBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"038db9ffe5356b0132253b84ed9a1e6f41819b8b25211161f9ca876247e5b65b","last_reissued_at":"2026-07-05T06:15:00.980884Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:00.980884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.18443","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:15:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iE8IfRG5Bq7KxjcPV1r1HzU1EWBjFWXoY4ZnLyLSOF6ngI5zDg/pjkP1rVnmD6hNtm1581oZfHIHRQnILqIWCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:10:14.230918Z"},"content_sha256":"bfd1a19ba3f995b6c2eee3e4dbb55ad7646f326b83f55a085903704bc9123c6c","schema_version":"1.0","event_id":"sha256:bfd1a19ba3f995b6c2eee3e4dbb55ad7646f326b83f55a085903704bc9123c6c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:AOG3T77FGVVQCMRFHOCO3GQ6N5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Off-Policy RL Algorithms Can be Sample-Efficient for Continuous Control via Sample Multiple Reuse","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiafei Lyu, Le Wan, Xiu Li, Zongqing Lu","submitted_at":"2023-05-29T03:25:22Z","abstract_excerpt":"Sample efficiency is one of the most critical issues for online reinforcement learning (RL). Existing methods achieve higher sample efficiency by adopting model-based methods, Q-ensemble, or better exploration mechanisms. We, instead, propose to train an off-policy RL agent via updating on a fixed sampled batch multiple times, thus reusing these samples and better exploiting them within a single optimization loop. We name our method sample multiple reuse (SMR). We theoretically show the properties of Q-learning with SMR, e.g., convergence. Furthermore, we incorporate SMR with off-the-shelf off"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18443","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/2305.18443/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":"2026-07-05T06:15:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jHSujunsyZNwAdY3wfhQhICQZQ35VOi/ygYYA4qMMr0IdXHFL0J3aRlKCePFkzaTFb7v4dvu6tU2C4SzdywICQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:10:14.231428Z"},"content_sha256":"84c4f6bebd06aa6256e369d6cfe13020108440be02eaba0a4d373e200e684764","schema_version":"1.0","event_id":"sha256:84c4f6bebd06aa6256e369d6cfe13020108440be02eaba0a4d373e200e684764"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AOG3T77FGVVQCMRFHOCO3GQ6N5/bundle.json","state_url":"https://pith.science/pith/AOG3T77FGVVQCMRFHOCO3GQ6N5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AOG3T77FGVVQCMRFHOCO3GQ6N5/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":"2026-08-09T16:10:14Z","links":{"resolver":"https://pith.science/pith/AOG3T77FGVVQCMRFHOCO3GQ6N5","bundle":"https://pith.science/pith/AOG3T77FGVVQCMRFHOCO3GQ6N5/bundle.json","state":"https://pith.science/pith/AOG3T77FGVVQCMRFHOCO3GQ6N5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AOG3T77FGVVQCMRFHOCO3GQ6N5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AOG3T77FGVVQCMRFHOCO3GQ6N5","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":"dd887a1737749b08f7967c6b98f089b16009d8abf5cc7d1d377c4826d89c4eb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-29T03:25:22Z","title_canon_sha256":"7b0c80249f63b7f85d5a71d391674b2c0776953d2a0f300915b31bc834f8e996"},"schema_version":"1.0","source":{"id":"2305.18443","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18443","created_at":"2026-07-05T06:15:00Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18443v1","created_at":"2026-07-05T06:15:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18443","created_at":"2026-07-05T06:15:00Z"},{"alias_kind":"pith_short_12","alias_value":"AOG3T77FGVVQ","created_at":"2026-07-05T06:15:00Z"},{"alias_kind":"pith_short_16","alias_value":"AOG3T77FGVVQCMRF","created_at":"2026-07-05T06:15:00Z"},{"alias_kind":"pith_short_8","alias_value":"AOG3T77F","created_at":"2026-07-05T06:15:00Z"}],"graph_snapshots":[{"event_id":"sha256:84c4f6bebd06aa6256e369d6cfe13020108440be02eaba0a4d373e200e684764","target":"graph","created_at":"2026-07-05T06:15:00Z","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/2305.18443/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sample efficiency is one of the most critical issues for online reinforcement learning (RL). Existing methods achieve higher sample efficiency by adopting model-based methods, Q-ensemble, or better exploration mechanisms. We, instead, propose to train an off-policy RL agent via updating on a fixed sampled batch multiple times, thus reusing these samples and better exploiting them within a single optimization loop. We name our method sample multiple reuse (SMR). We theoretically show the properties of Q-learning with SMR, e.g., convergence. Furthermore, we incorporate SMR with off-the-shelf off","authors_text":"Jiafei Lyu, Le Wan, Xiu Li, Zongqing Lu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-29T03:25:22Z","title":"Off-Policy RL Algorithms Can be Sample-Efficient for Continuous Control via Sample Multiple Reuse"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18443","kind":"arxiv","version":1},"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:bfd1a19ba3f995b6c2eee3e4dbb55ad7646f326b83f55a085903704bc9123c6c","target":"record","created_at":"2026-07-05T06:15:00Z","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":"dd887a1737749b08f7967c6b98f089b16009d8abf5cc7d1d377c4826d89c4eb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-29T03:25:22Z","title_canon_sha256":"7b0c80249f63b7f85d5a71d391674b2c0776953d2a0f300915b31bc834f8e996"},"schema_version":"1.0","source":{"id":"2305.18443","kind":"arxiv","version":1}},"canonical_sha256":"038db9ffe5356b0132253b84ed9a1e6f41819b8b25211161f9ca876247e5b65b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"038db9ffe5356b0132253b84ed9a1e6f41819b8b25211161f9ca876247e5b65b","first_computed_at":"2026-07-05T06:15:00.980884Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:15:00.980884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5SQFrGWX8PsYmA+G4gfFwHc5t9sA58KII2dgSOUWQ3y+AgvJaSIZZZcvNbZGFx6HeFlg72t2XZMCSmOyNB3TBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:15:00.981307Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.18443","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bfd1a19ba3f995b6c2eee3e4dbb55ad7646f326b83f55a085903704bc9123c6c","sha256:84c4f6bebd06aa6256e369d6cfe13020108440be02eaba0a4d373e200e684764"],"state_sha256":"7ae79661d785a3c2af16daa7f7bdbf70b936eb1af15d86ad2e94425d7d231ff0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2vGakEVlUui01ZKWMXM2Uq6Eu5ycoD5WSaumWrgTWfwjIEQrIAE7mXisH2aMYkcNbUZ6Ej4h/qlF84PcxaZWAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T16:10:14.235384Z","bundle_sha256":"f4e12e7095138c08c587508fe4b6d6b51c5cfa4ab75a1487422a193cc8910cc0"}}