Learning Latent State Spaces for Planning through Reward Prediction.

Aaron J. Havens Yi Ouyang Prabhat Nagarajan Yasuhiro Fujita

Published in: CoRR (2019)

Keyphrases

reinforcement learning
learning systems
state space
learning algorithm
supervised learning
learning problems
prior knowledge
learning process
online learning
heuristic search
dynamic programming
decision trees
machine learning
planning problems
long run
action selection
learning agent