{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SRQ5EFAEM6LJMOGUJNTLMTFMRC","short_pith_number":"pith:SRQ5EFAE","schema_version":"1.0","canonical_sha256":"9461d2140467969638d44b66b64cac8896077b35b9a629bda1c6f987c63a7463","source":{"kind":"arxiv","id":"1807.01672","version":3},"attestation_state":"computed","paper":{"title":"Ranked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alain-Sam Cohen, Alexandre Laterre, Amine Kerkeni, David Kas, Karim Beguir, Karl Hajjar, Mohamed Khalil Jabri, Torbjorn S. Dahl, Yunguan Fu","submitted_at":"2018-07-04T16:40:53Z","abstract_excerpt":"Adversarial self-play in two-player games has delivered impressive results when used with reinforcement learning algorithms that combine deep neural networks and tree search. Algorithms like AlphaZero and Expert Iteration learn tabula-rasa, producing highly informative training data on the fly. However, the self-play training strategy is not directly applicable to single-player games. Recently, several practically important combinatorial optimisation problems, such as the travelling salesman problem and the bin packing problem, have been reformulated as reinforcement learning problems, increas"},"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":"1807.01672","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T16:40:53Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"66de93e455004590ba0c3a8ce7358ef1c822921a06e47832b6394f5fadb73cbf","abstract_canon_sha256":"0805f05319c6e2f46b4570add9f3f2ec9a921640d67ce84c2d8326bf7e9e7f8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:52.657917Z","signature_b64":"8hbRYGSQcqb20LOGLgibOKwkXQghAgfYNjLhoOMb5eYj3x3u8zoGQ8qCCeSf57dqSP/nK9CjQeZ0xLMWQincDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9461d2140467969638d44b66b64cac8896077b35b9a629bda1c6f987c63a7463","last_reissued_at":"2026-05-17T23:58:52.657302Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:52.657302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ranked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alain-Sam Cohen, Alexandre Laterre, Amine Kerkeni, David Kas, Karim Beguir, Karl Hajjar, Mohamed Khalil Jabri, Torbjorn S. Dahl, Yunguan Fu","submitted_at":"2018-07-04T16:40:53Z","abstract_excerpt":"Adversarial self-play in two-player games has delivered impressive results when used with reinforcement learning algorithms that combine deep neural networks and tree search. Algorithms like AlphaZero and Expert Iteration learn tabula-rasa, producing highly informative training data on the fly. However, the self-play training strategy is not directly applicable to single-player games. Recently, several practically important combinatorial optimisation problems, such as the travelling salesman problem and the bin packing problem, have been reformulated as reinforcement learning problems, increas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01672","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":""},"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":"1807.01672","created_at":"2026-05-17T23:58:52.657398+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.01672v3","created_at":"2026-05-17T23:58:52.657398+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01672","created_at":"2026-05-17T23:58:52.657398+00:00"},{"alias_kind":"pith_short_12","alias_value":"SRQ5EFAEM6LJ","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"SRQ5EFAEM6LJMOGU","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"SRQ5EFAE","created_at":"2026-05-18T12:32:53.628368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10953","citing_title":"Diffusion Reinforcement Learning Based Online 3D Bin Packing Spatial Strategy Optimization","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SRQ5EFAEM6LJMOGUJNTLMTFMRC","json":"https://pith.science/pith/SRQ5EFAEM6LJMOGUJNTLMTFMRC.json","graph_json":"https://pith.science/api/pith-number/SRQ5EFAEM6LJMOGUJNTLMTFMRC/graph.json","events_json":"https://pith.science/api/pith-number/SRQ5EFAEM6LJMOGUJNTLMTFMRC/events.json","paper":"https://pith.science/paper/SRQ5EFAE"},"agent_actions":{"view_html":"https://pith.science/pith/SRQ5EFAEM6LJMOGUJNTLMTFMRC","download_json":"https://pith.science/pith/SRQ5EFAEM6LJMOGUJNTLMTFMRC.json","view_paper":"https://pith.science/paper/SRQ5EFAE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.01672&json=true","fetch_graph":"https://pith.science/api/pith-number/SRQ5EFAEM6LJMOGUJNTLMTFMRC/graph.json","fetch_events":"https://pith.science/api/pith-number/SRQ5EFAEM6LJMOGUJNTLMTFMRC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SRQ5EFAEM6LJMOGUJNTLMTFMRC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SRQ5EFAEM6LJMOGUJNTLMTFMRC/action/storage_attestation","attest_author":"https://pith.science/pith/SRQ5EFAEM6LJMOGUJNTLMTFMRC/action/author_attestation","sign_citation":"https://pith.science/pith/SRQ5EFAEM6LJMOGUJNTLMTFMRC/action/citation_signature","submit_replication":"https://pith.science/pith/SRQ5EFAEM6LJMOGUJNTLMTFMRC/action/replication_record"}},"created_at":"2026-05-17T23:58:52.657398+00:00","updated_at":"2026-05-17T23:58:52.657398+00:00"}