Login / Signup
Using multi-agent systems for learning optimal policies for complex problems.
Andreas Lommatzsch
Sahin Albayrak
Published in:
ACM Southeast Regional Conference (2007)
Keyphrases
</>
optimal policy
decision problems
reinforcement learning
multi agent systems
learning algorithm
search space
np complete
markov decision processes
learning rate
dynamic programming algorithms
average reward reinforcement learning
machine learning
cost function
dynamic programming
average reward