Login / Signup

Integral reinforcement learning off-policy method for solving nonlinear multi-player nonzero-sum games with saturated actuator.

He RenHuaguang ZhangYinlei WenChong Liu
Published in: Neurocomputing (2019)
Keyphrases
  • reinforcement learning
  • objective function
  • state space
  • multi agent
  • graph cuts
  • dynamic programming
  • game playing
  • model free
  • decomposition method
  • solving nonlinear