Online learning algorithms for reinforcement learning with function approximation
Reinforcement learning deals with the problem of sequential decision making in uncertain stochastic environments. In this thesis I deal with agents who attempt to solve the reinforcement learning problem online and in real-time. This presents experimental challenges for which I introduce novel kernelised algorithms. Kernel algorithms are very useful in reinforcement learning settings as they enable learning in situations where a very high-dimensional or hand engineered feature vector would...[Show more]
|Collections||Open Access Theses|
|Access Rights:||Open Access|
|b28789520_Robards_Matthew.pdf||31.07 MB||Adobe PDF|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.