Sign in
Monte Carlo preference elicitation for learning additive reward functions.
Stephanie Rosenthal
Manuela M. Veloso
Published in:
RO-MAN (2012)
Keyphrases
</>
monte carlo
inverse reinforcement learning
preference elicitation
reinforcement learning
learning algorithm
monte carlo simulation
markovian decision
state space
prior knowledge
reward function
markov chain
temporal difference
utility function
markov decision processes
monte carlo tree search