Login / Signup

An actor-critic algorithm for multi-agent learning in queue-based stochastic games.

Diatha Krishna SundarK. Ravikumar
Published in: Neurocomputing (2014)
Keyphrases
  • learning algorithm
  • np hard
  • dynamic programming
  • computational complexity
  • learning process
  • average reward
  • cooperative
  • search space
  • worst case
  • linear programming
  • path finding
  • stochastic games
  • multi agent learning