Fitted policy search

2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL) ◽

10.1109/adprl.2011.5967368 ◽

2011 ◽

Author(s):

Martino Migliavacca ◽

Alessio Pecorino ◽

Matteo Pirotta ◽

Marcello Restelli ◽

Andrea Bonarini

Keyword(s):

Download Full-text

Expectation-maximization Policy Search with Parameter-based Exploration

ACTA AUTOMATICA SINICA ◽

10.3724/sp.j.1004.2012.00038 ◽

2012 ◽

Vol 38 (1) ◽

pp. 38-45

Author(s):

Yu-Hu CHENG ◽

Huan-Ting FENG ◽

Xue-Song WANG

Keyword(s):

Expectation Maximization ◽

Download Full-text

Grid-Interactive Multi-Zone Building Control Using Reinforcement Learning with Global-Local Policy Search

2021 American Control Conference (ACC) ◽

10.23919/acc50511.2021.9482917 ◽

2021 ◽

Author(s):

Xiangyu Zhang ◽

Rohit Chintala ◽

Andrey Bernstein ◽

Peter Graf ◽

Xin Jin

Keyword(s):

Reinforcement Learning ◽

Local Policy ◽

Building Control ◽

Download Full-text

Efficient policy search in low-dimensional embedding spaces by generalizing motion primitives with a parameterized skill memory

Autonomous Robots ◽

10.1007/s10514-014-9417-9 ◽

2014 ◽

Vol 38 (4) ◽

pp. 331-348 ◽

Author(s):

René Felix Reinhart ◽

Jochen Jakob Steil

Keyword(s):

Motion Primitives ◽

Policy Search ◽

Low Dimensional ◽

Embedding Spaces

Download Full-text

Implementation of assembly task based on guided policy search algorithm

10.1109/iecon48115.2021.9589805 ◽

2021 ◽

Author(s):

Qingwei Dong ◽

Chuanzhi Zang ◽

Peng Zeng ◽

Guangxi Wan ◽

Yunpeng He ◽

...

Keyword(s):

Search Algorithm ◽

Policy Search ◽

Download Full-text

Efficient hierarchical MCMC for policy search

Twenty-first international conference on Machine learning - ICML '04 ◽

10.1145/1015330.1015381 ◽

2004 ◽

Author(s):

Malcolm Strens

Keyword(s):

Download Full-text

Numerical Quadrature for Probabilistic Policy Search

IEEE Transactions on Pattern Analysis and Machine Intelligence ◽

10.1109/tpami.2018.2879335 ◽

2020 ◽

Vol 42 (1) ◽

pp. 164-175 ◽

Author(s):

Julia Vinogradska ◽

Bastian Bischoff ◽

Jan Achterhold ◽

Torsten Koller ◽

Jan Peters

Keyword(s):

Numerical Quadrature ◽

Download Full-text

Approximate policy search with cross-entropy optimization of basis functions

Reinforcement Learning and Dynamic Programming Using Function Approximators ◽

10.1201/9781439821091-11 ◽

2017 ◽

pp. 219-248

Keyword(s):

Basis Functions ◽

Cross Entropy ◽

Policy Search ◽

Entropy Optimization

Download Full-text

A Comparison of Policy Search in Joint Space and Cartesian Space for Refinement of Skills

Advances in Service and Industrial Robotics - Advances in Intelligent Systems and Computing ◽

10.1007/978-3-030-19648-6_35 ◽

2019 ◽

pp. 301-309 ◽

Author(s):

Alexander Fabisch

Keyword(s):

Joint Space ◽

Policy Search ◽

Cartesian Space

Download Full-text

An Incremental Fast Policy Search Using a Single Sample Path

Lecture Notes in Computer Science - Pattern Recognition and Machine Intelligence ◽

10.1007/978-3-319-69900-4_1 ◽

2017 ◽

pp. 3-10

Author(s):

Ajin George Joseph ◽

Shalabh Bhatnagar

Keyword(s):

Sample Path ◽

Single Sample ◽

Download Full-text

Control of an Acrobot system using reinforcement learning with probabilistic policy search

10.1109/anzcc53563.2021.9628194 ◽

2021 ◽

Author(s):

N. Snehal ◽

W. Pooja ◽

K. Sonam ◽

S. R. Wagh ◽

N. M. Singh

Keyword(s):

Reinforcement Learning ◽

Download Full-text