Sign in

A Gradient Descent Sarsa(λ) Algorithm Based on the Adaptive Reward-shaping Mechanism.

Quan LiuQi-ming FuFei XiaoYuchen Fu
Published in: Intell. Autom. Soft Comput. (2013)
Keyphrases
  • cost function
  • dynamic programming
  • search space
  • learning algorithm
  • computational complexity
  • convergence rate
  • objective function
  • probabilistic model
  • monte carlo
  • dynamical systems
  • evaluation function