Login / Signup
Using State Predictions for Value Regularization in Curiosity Driven Deep Reinforcement Learning.
Gino Brunner
Manuel Fritsche
Oliver Richter
Roger Wattenhofer
Published in:
CoRR (2018)
Keyphrases
</>
reinforcement learning
state space
learning algorithm
data driven
cross validation
function approximation
data sets
machine learning
semi supervised learning
prior information
regularization parameter
deep learning
action space
transition model