Login / Signup
Event-Detecting Multi-Agent MDPs: Complexity and Constant-Factor Approximations.
Akshat Kumar
Shlomo Zilberstein
Published in:
IJCAI (2009)
Keyphrases
</>
training set
constant factor
multi agent
worst case
reinforcement learning
approximation algorithms
markov decision processes
supervised learning
data sets
active learning
state space
search algorithm
decision problems
search space
evolutionary algorithm
linear programming
online learning
optimal policy
single agent