Neural combinatorial optimization with reinforcement learning

5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings

Volumn , Issue , 2017, Pages

  Bello, Irwan ^a   Pham, Hieu ^a   Le, Quoc V ^a   Norouzi, Mohammad ^a   Bengio, Samy ^a  

^a GOOGLE INC   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

GRADIENT METHODS; RECURRENT NEURAL NETWORKS; REINFORCEMENT LEARNING; TRAVELING SALESMAN PROBLEM;

COMBINATORIAL OPTIMIZATION PROBLEMS; EUCLIDEAN GRAPH; GENERAL TOOLS; NEURAL NETWORK LEARNING; NEURAL-NETWORKS; OPTIMAL RESULTS; POLICY GRADIENT METHODS; REINFORCEMENT LEARNINGS; STATE OF THE ART;

COMBINATORIAL OPTIMIZATION;

EID: 85140424199     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (8)

1. David L Applegate, Robert E Bixby, Vasek Chvatal, and William J Cook. Concorde tsp solver, 2006. URL www.math.uwaterloo.ca/tsp/concorde.
2. Google. Or-tools, google optimization tools, 2016. URL https://developers.google.com/optimization/routing.
3. Keld Helsgaun. An effective implementation of the Lin-Kernighan traveling salesman. European Journal of Operational Research, 126:106-130, 2000.
4. Keld Helsgaun. LK-H, 2012. URL http://akira.ruc.dk/keld/research/LKH/.
5. Sepp Hochreiter and Jurgen Schmidhuber. Long short-term memory. Neural Computations, 1997.
6. Diederik Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In ICLR, 2014.
7. Oriol Vinyals, Meire Fortunato, and Navdeep Jaitly. Pointer networks. In Advances in Neural Information Processing Systems, pp. 2692-2700, 2015.
8. Ronald Williams. Simple statistical gradient following algorithms for connectionnist reinforcement learning. In Machine Learning, 1992.