scholarly journals Logarithmic Regret for Episodic Continuous-Time Linear-Quadratic Reinforcement Learning Over a Finite-Time Horizon

2021 ◽  
Author(s):  
Matteo Basei ◽  
Xin Guo ◽  
Anran Hu ◽  
Yufei Zhang
Keyword(s):  
Reinforcement Learning ◽  
Continuous Time ◽  
Finite Time ◽  
Time Horizon ◽  
Linear Quadratic ◽  
Finite Time Horizon ◽  
Time Linear

scholarly journals A Constrained Markovian Diffusion Model for Controlling the Pollution Accumulation

Mathematics ◽  
2021 ◽  
Vol 9 (13) ◽  
pp. 1466
Author(s):  
Beatris Adriana Escobedo-Trujillo ◽  
José Daniel López-Barrientos ◽  
Javier Garrido-Meléndez
Keyword(s):  
Dynamic Programming ◽  
Dirichlet Problem ◽  
Stochastic Control ◽  
Finite Time ◽  
Time Horizon ◽  
Closed Loop ◽  
Programming Techniques ◽  
Pollution Accumulation ◽  
Finite Time Horizon ◽  
The Cost

This work presents a study of a finite-time horizon stochastic control problem with restrictions on both the reward and the cost functions. To this end, it uses standard dynamic programming techniques, and an extension of the classic Lagrange multipliers approach. The coefficients considered here are supposed to be unbounded, and the obtained strategies are of non-stationary closed-loop type. The driving thread of the paper is a sequence of examples on a pollution accumulation model, which is used for the purpose of showing three algorithms for the purpose of replicating the results. There, the reader can find a result on the interchangeability of limits in a Dirichlet problem.

Sign in / Sign up

Export Citation Format

Share Document