Experience replay for least-squares policy iteration

  title={Experience replay for least-squares policy iteration},
  author={Quan Liu and Xin Long Zhou and Fei Zhu and Qiming Fu and Yuchen Fu},
  journal={IEEE/CAA Journal of Automatica Sinica},
Policy iteration, which evaluates and improves the control policy iteratively, is a reinforcement learning method. Policy evaluation with the least-squares method can draw more useful information from the empirical data and therefore improve the data validity. However, most existing online least-squares policy iteration methods only use each sample just once, resulting in the low utilization rate. With the goal of improving the utilization efficiency, we propose an experience replay for least… CONTINUE READING


Publications citing this paper.
Showing 1-2 of 2 extracted citations

Neural Information Processing

Lecture Notes in Computer Science • 2016
View 9 Excerpts
Highly Influenced

Game theoretic Lyapunov fuzzy control for Inverted Pendulum

2015 4th International Conference on Reliability, Infocom Technologies and Optimization (ICRITO) (Trends and Future Directions) • 2015
View 1 Excerpt


Publications referenced by this paper.
Showing 1-10 of 18 references

Reinforcement Learning and Dynamic Programming using Function Approximators

L Busoniu, R Babuska, B De Schutter, D. Ernst
View 9 Excerpts
Highly Influenced

A least square actor-critic approach for continuous action space

Zhu Fei, Liu Quan, Fu Qi-Ming, Fu Yu-Chen
Journal of Computer Research and Development, • 2014

Least-squares temporal difference learning based on an extreme learning

P Escandell-Montero, J DMartı́nez-Martı́nez, E Soria-Olivas, J. Gómez- Sanchis
machine. Neurocomputing, • 2014

Data-based self-learning optimal control: research progress and prospects

Liu De-Rong, Li Hong-Liang, Wang Ding
Acta Automatica Sinica, • 2013

Tracking learning based on Gaussian regression for multi-agent systems in continuous space

Chen Xin, Wei Hai-Jun, Wu Min, Cao Wei-Hua
Acta Automatica Sinica, • 2013

A hybrid transfer algorithm for reinforcement learning based on spectral method

Zhu Mei-Qiang, Cheng Yu-Hu, Li Ming, Wang Xue-Song, Feng Huan- Ting
Acta Automatica Sinica, • 2012

Similar Papers

Loading similar papers…