Login / Signup

Comparing Multi-Armed Bandit Algorithms and Q-learning for Multiagent Action Selection: a Case Study in Route Choice.

Thiago B. F. de OliveiraAna L. C. BazzanBruno C. da SilvaRicardo Grunitzki
Published in: IJCNN (2018)
Keyphrases
  • action selection
  • multi agent
  • multi armed bandit
  • reinforcement learning
  • learning algorithm
  • cooperative
  • basal ganglia
  • decision making
  • probabilistic model
  • function approximation