Login / Signup

Experimental analysis on Sarsa(lambda) and Q(lambda) with different eligibility traces strategies.

Jinsong LengColin FyfeLakhmi C. Jain
Published in: J. Intell. Fuzzy Syst. (2009)
Keyphrases
  • eligibility traces
  • reinforcement learning algorithms
  • reinforcement learning
  • fixed point
  • markov decision processes
  • function approximation
  • learning algorithm
  • dynamic environments
  • reinforcement learning methods