Login / Signup
On the Difficulty of Achieving Equilibrium in Interactive POMDPs.
Prashant Doshi
Piotr J. Gmytrasiewicz
Published in:
AI&M (2006)
Keyphrases
</>
reinforcement learning
virtual reality
user friendly
data sets
genetic algorithm
state space
computer graphics
belief state
learning algorithm
game theory
nash equilibrium
optimal control
partially observable markov decision processes