2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)

2014 ◽

Author(s):

Ali Heydari

Keyword(s):

Reinforcement Learning ◽

Theoretical Analysis ◽

Switching Scheme

Download Full-text

Active learning for classification: An optimistic approach

2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL) ◽

10.1109/adprl.2014.7010610 ◽

2014 ◽

Cited By ~ 2

Author(s):

Timothe Collet ◽

Olivier Pietquin

Keyword(s):

Active Learning

Download Full-text

Pareto Upper Confidence Bounds algorithms: An empirical study

2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL) ◽

10.1109/adprl.2014.7010620 ◽

2014 ◽

Cited By ~ 2

Author(s):

Madalina M Drugan ◽

Ann Nowe ◽

Bernard Manderick

Keyword(s):

Empirical Study ◽

Confidence Bounds

Download Full-text

Model-free Q-learning over finite horizon for uncertain linear continuous-time systems

2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL) ◽

10.1109/adprl.2014.7010629 ◽

2014 ◽

Author(s):

Hao Xu ◽

S. Jagannathan

Keyword(s):

Continuous Time ◽

Finite Horizon ◽

Q Learning ◽

Model Free ◽

Continuous Time Systems ◽

Time Systems

Download Full-text

An analysis of optimistic, best-first search for minimax sequential decision making

2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL) ◽

10.1109/adprl.2014.7010615 ◽

2014 ◽

Cited By ~ 4

Author(s):

Lucian Busoniu ◽

Remi Munos ◽

Elod Pall

Keyword(s):

Decision Making ◽

Sequential Decision Making ◽

Sequential Decision ◽

Best First Search

Download Full-text

Optimal self-learning battery control in smart residential grids by iterative Q-learning algorithm

2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL) ◽

10.1109/adprl.2014.7010630 ◽

2014 ◽

Cited By ~ 1

Author(s):

Qinglai Wei ◽

Derong Liu ◽

Guang Shi ◽

Yu Liu ◽

Qiang Guan

Keyword(s):

Learning Algorithm ◽

Q Learning ◽

Self Learning

Download Full-text

Using supervised training signals of observable state dynamics to speed-up and improve reinforcement learning

2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL) ◽

10.1109/adprl.2014.7010640 ◽

2014 ◽

Cited By ~ 2

Author(s):

Daniel L Elliott ◽

Charles Anderson

Keyword(s):

Reinforcement Learning ◽

Supervised Training ◽

Speed Up ◽

Observable State

Download Full-text

Tunable and generic problem instance generation for multi-objective reinforcement learning

2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL) ◽

10.1109/adprl.2014.7010646 ◽

2014 ◽

Cited By ~ 2

Author(s):

Deon Garrett ◽

Jordi Bieger ◽

Kristinn R. Thorisson

Keyword(s):

Reinforcement Learning ◽

Problem Instance ◽

Multi Objective ◽

Instance Generation ◽

Generic Problem

Download Full-text

Policy gradient approaches for multi-objective sequential decision making: A comparison

2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL) ◽

10.1109/adprl.2014.7010618 ◽

2014 ◽

Author(s):

Simone Parisi ◽

Matteo Pirotta ◽

Nicola Smacchia ◽

Luca Bascetta ◽

Marcello Restelli

Keyword(s):

Decision Making ◽

Sequential Decision Making ◽

Sequential Decision ◽

Multi Objective ◽

Policy Gradient

Download Full-text

Data-driven partially observable dynamic processes using adaptive dynamic programming

2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL) ◽

10.1109/adprl.2014.7010628 ◽

2014 ◽

Cited By ~ 4

Author(s):

Xiangnan Zhong ◽

Zhen Ni ◽

Yufei Tang ◽

Haibo He

Keyword(s):

Dynamic Programming ◽

Adaptive Dynamic Programming ◽

Data Driven ◽

Dynamic Processes ◽

Adaptive Dynamic ◽

Partially Observable

Download Full-text

2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)
Latest Publications

TOTAL DOCUMENTS

H-INDEX

Published By IEEE

Theoretical analysis of a reinforcement learning based switching scheme

Active learning for classification: An optimistic approach

Pareto Upper Confidence Bounds algorithms: An empirical study

Model-free Q-learning over finite horizon for uncertain linear continuous-time systems

An analysis of optimistic, best-first search for minimax sequential decision making

Optimal self-learning battery control in smart residential grids by iterative Q-learning algorithm

Using supervised training signals of observable state dynamics to speed-up and improve reinforcement learning

Tunable and generic problem instance generation for multi-objective reinforcement learning

Policy gradient approaches for multi-objective sequential decision making: A comparison

Data-driven partially observable dynamic processes using adaptive dynamic programming

Export Citation Format

2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)Latest Publications

TOTAL DOCUMENTS

H-INDEX

Published By IEEE

Theoretical analysis of a reinforcement learning based switching scheme

Active learning for classification: An optimistic approach

Pareto Upper Confidence Bounds algorithms: An empirical study

Model-free Q-learning over finite horizon for uncertain linear continuous-time systems

An analysis of optimistic, best-first search for minimax sequential decision making

Optimal self-learning battery control in smart residential grids by iterative Q-learning algorithm

Using supervised training signals of observable state dynamics to speed-up and improve reinforcement learning

Tunable and generic problem instance generation for multi-objective reinforcement learning

Policy gradient approaches for multi-objective sequential decision making: A comparison

Data-driven partially observable dynamic processes using adaptive dynamic programming

2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)
Latest Publications