{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WB2RUFIP7WUFPWZQKJHO4YS4S7","short_pith_number":"pith:WB2RUFIP","schema_version":"1.0","canonical_sha256":"b0751a150ffda857db30524eee625c97dd5cee5321865d11be0cc58f048334d1","source":{"kind":"arxiv","id":"2306.01276","version":4},"attestation_state":"computed","paper":{"title":"Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hyeonah Kim, Jinkyoo Park, Minsu Kim, Sungsoo Ahn","submitted_at":"2023-06-02T05:34:01Z","abstract_excerpt":"Deep reinforcement learning (DRL) has significantly advanced the field of combinatorial optimization (CO). However, its practicality is hindered by the necessity for a large number of reward evaluations, especially in scenarios involving computationally intensive function assessments. To enhance the sample efficiency, we propose a simple but effective method, called symmetric replay training (SRT), which can be easily integrated into various DRL methods. Our method leverages high-reward samples to encourage exploration of the under-explored symmetric regions without additional online interacti"},"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":"2306.01276","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-02T05:34:01Z","cross_cats_sorted":[],"title_canon_sha256":"ba23360d9d1ec0df4915f7926579d6671c2b1fdf47fc23f629b21e70e43a1a86","abstract_canon_sha256":"1208f8007136027891c0e8d63d9ec08dfd9a1a6052dfdf6035ee7076af16f7a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:46.411839Z","signature_b64":"3yd2ddtqbtD0EtxTo5NKXdl+a1HhxieXjEuof2l4hql3y3BV1TNjaGAQmNUb4MyVHZeG0NvtXfkHKfrel704DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0751a150ffda857db30524eee625c97dd5cee5321865d11be0cc58f048334d1","last_reissued_at":"2026-07-05T08:44:46.411390Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:46.411390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hyeonah Kim, Jinkyoo Park, Minsu Kim, Sungsoo Ahn","submitted_at":"2023-06-02T05:34:01Z","abstract_excerpt":"Deep reinforcement learning (DRL) has significantly advanced the field of combinatorial optimization (CO). However, its practicality is hindered by the necessity for a large number of reward evaluations, especially in scenarios involving computationally intensive function assessments. To enhance the sample efficiency, we propose a simple but effective method, called symmetric replay training (SRT), which can be easily integrated into various DRL methods. Our method leverages high-reward samples to encourage exploration of the under-explored symmetric regions without additional online interacti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01276","kind":"arxiv","version":4},"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/2306.01276/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":"2306.01276","created_at":"2026-07-05T08:44:46.411450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.01276v4","created_at":"2026-07-05T08:44:46.411450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01276","created_at":"2026-07-05T08:44:46.411450+00:00"},{"alias_kind":"pith_short_12","alias_value":"WB2RUFIP7WUF","created_at":"2026-07-05T08:44:46.411450+00:00"},{"alias_kind":"pith_short_16","alias_value":"WB2RUFIP7WUFPWZQ","created_at":"2026-07-05T08:44:46.411450+00:00"},{"alias_kind":"pith_short_8","alias_value":"WB2RUFIP","created_at":"2026-07-05T08:44:46.411450+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.00700","citing_title":"DGA$_2$D: Directed Graph-Guided Automated Algorithm Design with Large Language Models","ref_index":67,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WB2RUFIP7WUFPWZQKJHO4YS4S7","json":"https://pith.science/pith/WB2RUFIP7WUFPWZQKJHO4YS4S7.json","graph_json":"https://pith.science/api/pith-number/WB2RUFIP7WUFPWZQKJHO4YS4S7/graph.json","events_json":"https://pith.science/api/pith-number/WB2RUFIP7WUFPWZQKJHO4YS4S7/events.json","paper":"https://pith.science/paper/WB2RUFIP"},"agent_actions":{"view_html":"https://pith.science/pith/WB2RUFIP7WUFPWZQKJHO4YS4S7","download_json":"https://pith.science/pith/WB2RUFIP7WUFPWZQKJHO4YS4S7.json","view_paper":"https://pith.science/paper/WB2RUFIP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.01276&json=true","fetch_graph":"https://pith.science/api/pith-number/WB2RUFIP7WUFPWZQKJHO4YS4S7/graph.json","fetch_events":"https://pith.science/api/pith-number/WB2RUFIP7WUFPWZQKJHO4YS4S7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WB2RUFIP7WUFPWZQKJHO4YS4S7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WB2RUFIP7WUFPWZQKJHO4YS4S7/action/storage_attestation","attest_author":"https://pith.science/pith/WB2RUFIP7WUFPWZQKJHO4YS4S7/action/author_attestation","sign_citation":"https://pith.science/pith/WB2RUFIP7WUFPWZQKJHO4YS4S7/action/citation_signature","submit_replication":"https://pith.science/pith/WB2RUFIP7WUFPWZQKJHO4YS4S7/action/replication_record"}},"created_at":"2026-07-05T08:44:46.411450+00:00","updated_at":"2026-07-05T08:44:46.411450+00:00"}