Login / Signup
Exploration-exploitation trade-off for continuous-time episodic reinforcement learning with linear-convex models.
Lukasz Szpruch
Tanut Treetanthiploet
Yufei Zhang
Published in:
CoRR (2021)
Keyphrases
</>
reinforcement learning
probabilistic model
linear model
linear models
machine learning
learning process
model selection
complex systems
optimal control
neural network
prior knowledge
machine learning algorithms
regression model
semi infinite programming