Login / Signup
The Thing that we Tried Didn't Work very Well: Deictic Representation in Reinforcement Learning.
Sarah Finney
Natalia Gardiol
Leslie Pack Kaelbling
Tim Oates
Published in:
UAI (2002)
Keyphrases
</>
reinforcement learning
function approximation
learning process
learning algorithm
neural network
social networks
information systems
three dimensional
multi agent
feature space
state space
markov decision processes