Title :
Abstract State Spaces with History
Author :
Timmer, Stephan ; Riedmiller, Martin
Author_Institution :
Dept. of Cognitive Sci., Osnabruck Univ.
Abstract :
In this article, we consider learning problems in which the learning agent has only imprecise information about the current state of the environment. To deal with the uncertainty of the agent, an abstract representation of the state space is built which can be used to define near optimal policies. Starting with only a few abstract states, the state space is incrementally refined by employing statistical tests. Parallel to the refinement process, a model-free reinforcement learning algorithm is used to learn a policy
Keywords :
Markov processes; learning (artificial intelligence); set theory; abstract representation; abstract state spaces; learning agent; model-free reinforcement learning algorithm; refinement process; statistical tests; Cognitive science; Data structures; History; Learning; Probability distribution; State-space methods; Tellurium; Testing; Uncertainty;
Conference_Titel :
Fuzzy Information Processing Society, 2006. NAFIPS 2006. Annual meeting of the North American
Conference_Location :
Montreal, Que.
Print_ISBN :
1-4244-0363-4
Electronic_ISBN :
1-4244-0363-4
DOI :
10.1109/NAFIPS.2006.365488
