%Aigaion2 BibTeX export from Idiap Publications %Thursday 21 November 2024 12:57:08 PM @ARTICLE{Wawrzynski_NN_2013, author = {Wawrzy{\'{n}}ski, P. and Tanwani, Ajay Kumar}, keywords = {Actor–critic, Autonomous learning, reinforcement learning, Step-size estimation}, projects = {Idiap}, month = may, title = {Autonomous reinforcement learning with experience replay}, journal = {Neural Networks}, volume = {41}, number = {0}, year = {2013}, pages = {156 - 167}, note = {Special Issue on Autonomous Learning}, issn = {0893-6080}, url = {http://www.sciencedirect.com/science/article/pii/S0893608012002936}, 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.} }