Pointer Networks with Q-Learning for Combinatorial Optimization

[2311.02629] Pointer Networks with Q-Learning for Combinatorial Optimization Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2311.02629 (cs) This paper has been withdrawn by Alessandro Barro [Submitted on 5 Nov 2023 ( v1 ), last revised 16 Aug 2026 (this version, v5)] Title: Pointer Networks with Q-Learning for Combinatorial Optimization Authors: Alessandro Barro View a PDF of the paper titled Pointer Networks with Q-Learning for Combinatorial Optimization, by Alessandro Barro No PDF available, click to view other formats Abstract: We introduce the Pointer Q-Network (PQN), a hybrid neural architecture that integrates model-free Q-value policy approximation with Pointer Networks (Ptr-Nets) to enhance the optimality of attention-based sequence generation, focusing on long-term outcomes. This integration proves particularly effective in solving combinatorial optimization (CO) tasks, especially the Travelling Salesman Problem (TSP), which is the focus of our study. We address this challenge by defining a Markov Decision Process (MDP) compatible with PQN, which involves iterative graph embedding, encoding and decoding by an LSTM-based recurrent neural network. This process generates a context vector and computes raw attention scores, which are dynamically adjusted by Q-values calculated for all available state-action pairs before applying softmax. The resulting attention vector is utilized as an action distribution, with actions selected hinged to exploration-exploitation dynamic adaptibility of PQN. Our empirical results demonstrate the efficacy of this approach, also testing the model in unstable environments. Comments: The author has identified limitations in the experimental methodology and evaluation, as well as conclusions that are not sufficiently supported by the available evidence. The manuscript is therefore being withdrawn, as it no longer meets the author's standards for scientific rigor Subjects: Machine Learning (cs.LG) ; Optimization and Control (math.OC) Cite as: arXiv:2311.02629 [cs.LG] (or arXiv:2311.02629v5 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2311.02629 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Alessandro Barro [ view email ] [v1] Sun, 5 Nov 2023 12:03:58 UTC (242 KB) [v2] Tue, 19 Mar 2024 09:15:36 UTC (199 KB) [v3] Mon, 17 Jun 2024 10:27:54 UTC (1,702 KB) [v4] Thu, 24 Oct 2024 17:25:19 UTC (1,703 KB) [v5] Sun, 16 Aug 2026 08:25:31 UTC (1 KB) (withdrawn) Full-text links: Access Paper: View a PDF of the paper titled Pointer Networks with Q-Learning for Combinatorial Optimization, by Alessandro Barro Withdrawn No license for this version due to withdrawn Current browse context: cs.LG < prev | next > new | recent | 2023-11 Change to browse by: cs math math.OC References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Pointer Networks with Q-Learning for Combinatorial Optimization#611235
• Quantum Maximum Entropy Inference and Hamiltonian Learning#670287
• Quantum Maximum Entropy Inference and Hamiltonian Learning#668222
• Q-learning#7267
• Heavy-Ball Q-Learning with Residual Weighting Correction#310829