scholarly journals Stochastic Optimal Growth with a Non-Compact State Space

2005 ◽  
Author(s):  
Yuzhe Zhang
Author(s):  
Hanhua Zhu

Deep reinforcement learning (DRL) increases the successful applications of reinforcement learning (RL) techniques but also brings challenges such as low sample efficiency. In this work, I propose generalized representation learning methods to obtain compact state space suitable for RL from a raw observation state. I expect my new methods will increase sample efficiency of RL by understandable representations of state and therefore improve the performance of RL.


2009 ◽  
Vol 10 (4) ◽  
pp. 384-400 ◽  
Author(s):  
Thorsten Pampel

Abstract We show for a class of basic growth models that convergence in ratios does not imply the pathwise convergence to the corresponding balanced growth path in the state space. We derive conditions on parameters and on the elasticity of the savings function for convergence or divergence and apply our results to the Solow model, an augmented Solow model as well as to an optimal growth model. An implication for the convergence debate is that two economies that differ only in the initial capital stock and converge in per capita terms might diverge to infinity in absolute terms.


2018 ◽  
Vol 23 (0) ◽  
Author(s):  
Paul Krühner ◽  
Martin Larsson

Author(s):  
Kazuo Nishimura ◽  
Ryszard Rudnicki ◽  
John Stachurski

Sign in / Sign up

Export Citation Format

Share Document