Autonomous reinforcement learning with experience replay
| Type of publication: | Journal paper |
| Citation: | Wawrzynski_NN_2013 |
| Publication status: | Published |
| Journal: | Neural Networks |
| Volume: | 41 |
| Year: | 2013 |
| Month: | May |
| Pages: | 156 - 167 |
| Note: | Special Issue on Autonomous Learning |
| ISSN: | 0893-6080 |
| URL: | http://www.sciencedirect.com/s... |
| DOI: | http://dx.doi.org/10.1016/j.neunet.2012.11.007 |
| Abstract: | This paper considers the issues of efficiency and autonomy that are required to make reinforcement learning suitable for real-life control tasks. A real-time reinforcement learning algorithm is presented that repeatedly adjusts the control policy with the use of previously collected samples, and autonomously estimates the appropriate step-sizes for the learning updates. The algorithm is based on the actor–critic with experience replay whose step-sizes are determined on-line by an enhanced fixed point algorithm for on-line neural network training. An experimental study with simulated octopus arm and half-cheetah demonstrates the feasibility of the proposed algorithm to solve difficult learning control problems in an autonomous way within reasonably short time. |
| Keywords: | Actor–critic, Autonomous learning, reinforcement learning, Step-size estimation |
| Projects: |
Idiap |
| Authors: | |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
Notes
|
|
|
|
|