Login / Signup
Reconciling Rewards with Predictive State Representations.
Andrea Baisero
Christopher Amato
Published in:
IJCAI (2021)
Keyphrases
</>
predictive state representations
dynamical systems
reinforcement learning
stochastic systems
temporal difference
markov decision processes
partially observable markov decision processes
past observations
state space
machine learning
computational complexity
function approximation
latent variable models