English

Ergodic Annealing

Artificial Intelligence 2020-08-04 v1 Theoretical Economics Probability Machine Learning

Abstract

Simulated Annealing is the crowning glory of Markov Chain Monte Carlo Methods for the solution of NP-hard optimization problems in which the cost function is known. Here, by replacing the Metropolis engine of Simulated Annealing with a reinforcement learning variation -- that we call Macau Algorithm -- we show that the Simulated Annealing heuristic can be very effective also when the cost function is unknown and has to be learned by an artificial agent.

Keywords

Cite

@article{arxiv.2008.00234,
  title  = {Ergodic Annealing},
  author = {Carlo Baldassi and Fabio Maccheroni and Massimo Marinacci and Marco Pirazzini},
  journal= {arXiv preprint arXiv:2008.00234},
  year   = {2020}
}
R2 v1 2026-06-23T17:34:23.132Z