Login / Signup

Learning Heuristics for the TSP by Policy Gradient.

Michel DeudonPierre CournutAlexandre LacosteYossiri AdulyasakLouis-Martin Rousseau
Published in: CPAIOR (2018)
Keyphrases
  • policy gradient
  • reinforcement learning
  • actor critic
  • learning process
  • supervised learning
  • learning tasks
  • search algorithm
  • cost function
  • metaheuristic
  • policy gradient methods