{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:3IEAO2EJ6EFHM63E3FFLG32XLC","short_pith_number":"pith:3IEAO2EJ","schema_version":"1.0","canonical_sha256":"da08076889f10a767b64d94ab36f5758a8f2b3f6961bef3dd1089b96a9169187","source":{"kind":"arxiv","id":"1611.09940","version":3},"attestation_state":"computed","paper":{"title":"Neural Combinatorial Optimization with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Hieu Pham, Irwan Bello, Mohammad Norouzi, Quoc V. Le, Samy Bengio","submitted_at":"2016-11-29T23:22:39Z","abstract_excerpt":"This paper presents a framework to tackle combinatorial optimization problems using neural networks and reinforcement learning. We focus on the traveling salesman problem (TSP) and train a recurrent network that, given a set of city coordinates, predicts a distribution over different city permutations. Using negative tour length as the reward signal, we optimize the parameters of the recurrent network using a policy gradient method. We compare learning the network parameters on a set of training graphs against learning them on individual test graphs. Despite the computational expense, without "},"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":"1611.09940","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-29T23:22:39Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"f3eca53324eabb3e7647472fc3ab8d139484e9b5db91a52d8ee97633ce309289","abstract_canon_sha256":"09d46aa188821cce9697528d278c36df1789c202df9d40b0ef1b215b349c8877"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:54.930616Z","signature_b64":"Wi8Hk/TbFmbrd/yzNgiOCxFLFpmexpDKJFw+0hgPhc+aaos/Ru+bEKd6eLPfKkRKycDEdcR3LUPXMRpQTdz2Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da08076889f10a767b64d94ab36f5758a8f2b3f6961bef3dd1089b96a9169187","last_reissued_at":"2026-05-18T00:52:54.930062Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:54.930062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Combinatorial Optimization with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Hieu Pham, Irwan Bello, Mohammad Norouzi, Quoc V. Le, Samy Bengio","submitted_at":"2016-11-29T23:22:39Z","abstract_excerpt":"This paper presents a framework to tackle combinatorial optimization problems using neural networks and reinforcement learning. We focus on the traveling salesman problem (TSP) and train a recurrent network that, given a set of city coordinates, predicts a distribution over different city permutations. Using negative tour length as the reward signal, we optimize the parameters of the recurrent network using a policy gradient method. We compare learning the network parameters on a set of training graphs against learning them on individual test graphs. Despite the computational expense, without "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.09940","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":"1611.09940","created_at":"2026-05-18T00:52:54.930155+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.09940v3","created_at":"2026-05-18T00:52:54.930155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.09940","created_at":"2026-05-18T00:52:54.930155+00:00"},{"alias_kind":"pith_short_12","alias_value":"3IEAO2EJ6EFH","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_16","alias_value":"3IEAO2EJ6EFHM63E","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_8","alias_value":"3IEAO2EJ","created_at":"2026-05-18T12:29:55.572404+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":30,"internal_anchor_count":16,"sample":[{"citing_arxiv_id":"1906.11080","citing_title":"AGAN: Towards Automated Design of Generative Adversarial Networks","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23395","citing_title":"Convex Compositional Reasoning Models","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"1907.08686","citing_title":"Combinatorial Keyword Recommendations for Sponsored Search with Deep Reinforcement Learning","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2406.11452","citing_title":"Attention-Based Deep Reinforcement Learning for Qubit Allocation in Modular Quantum Architectures","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2411.19517","citing_title":"RL-SPH: Learning to Achieve Feasible Solutions for Integer Linear Programs","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17539","citing_title":"Memory-Guided Tree Search with Cross-Branch Knowledge Transfer for LLM Solver Synthesis","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15899","citing_title":"Solving Classical and Quantum Spin Glasses with Deep Boltzmann Quantum States","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2506.09323","citing_title":"Learning-Optimized Qubit Mapping and Reuse to Minimize Inter-Core Communication in Modular Quantum Architectures","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2601.16175","citing_title":"Learning to Discover at Test Time","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2602.13155","citing_title":"Learning to Approximate Uniform Facility Location via Graph Neural Networks","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2602.20730","citing_title":"Rethinking Efficiency in Neural Combinatorial Optimization: Batched Preference Optimization with Mamba","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04940","citing_title":"ReVEL: Multi-Turn Reflective LLM-Guided Heuristic Evolution via Structured Performance Feedback","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2412.03555","citing_title":"PaliGemma 2: A Family of Versatile VLMs for Transfer","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13932","citing_title":"Rethinking Molecular OOD Generalization via Target-Aware Source Selection","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2509.24527","citing_title":"Training Agents Inside of Scalable World Models","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13638","citing_title":"CO-MAP: A Reinforcement Learning Approach to the Qubit Allocation Problem","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03614","citing_title":"Neural Global Optimization via Iterative Refinement from Noisy Samples","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09112","citing_title":"Contextual Plackett-Luce: An Efficient Neural Model for Probabilistic Sequence Selection under Ambiguity","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08404","citing_title":"Built Environment Reasoning from Remote Sensing Imagery Using Large Vision--Language Models","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22208","citing_title":"Finite Expression Method with TranNet-based Function Learning for High-Dimensional Partial Differential Equations","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05330","citing_title":"Graph Normalization: Fast Binarizing Dynamics for Differentiable MWIS","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04225","citing_title":"ARMATA: Auto-Regressive Multi-Agent Task Assignment","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22107","citing_title":"A Hybrid Reinforcement and Self-Supervised Learning Aided Benders Decomposition Algorithm","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20236","citing_title":"Machine Learning for Two-Stage Graph Sparsification for the Travelling Salesman Problem","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20109","citing_title":"Learning to Solve the Quadratic Assignment Problem with Warm-Started MCMC Finetuning","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3IEAO2EJ6EFHM63E3FFLG32XLC","json":"https://pith.science/pith/3IEAO2EJ6EFHM63E3FFLG32XLC.json","graph_json":"https://pith.science/api/pith-number/3IEAO2EJ6EFHM63E3FFLG32XLC/graph.json","events_json":"https://pith.science/api/pith-number/3IEAO2EJ6EFHM63E3FFLG32XLC/events.json","paper":"https://pith.science/paper/3IEAO2EJ"},"agent_actions":{"view_html":"https://pith.science/pith/3IEAO2EJ6EFHM63E3FFLG32XLC","download_json":"https://pith.science/pith/3IEAO2EJ6EFHM63E3FFLG32XLC.json","view_paper":"https://pith.science/paper/3IEAO2EJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.09940&json=true","fetch_graph":"https://pith.science/api/pith-number/3IEAO2EJ6EFHM63E3FFLG32XLC/graph.json","fetch_events":"https://pith.science/api/pith-number/3IEAO2EJ6EFHM63E3FFLG32XLC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3IEAO2EJ6EFHM63E3FFLG32XLC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3IEAO2EJ6EFHM63E3FFLG32XLC/action/storage_attestation","attest_author":"https://pith.science/pith/3IEAO2EJ6EFHM63E3FFLG32XLC/action/author_attestation","sign_citation":"https://pith.science/pith/3IEAO2EJ6EFHM63E3FFLG32XLC/action/citation_signature","submit_replication":"https://pith.science/pith/3IEAO2EJ6EFHM63E3FFLG32XLC/action/replication_record"}},"created_at":"2026-05-18T00:52:54.930155+00:00","updated_at":"2026-05-18T00:52:54.930155+00:00"}