Function approximation is an interesting topic. On the one hand you are looking for a function that approximates arbitrary data, can handle multi-dimensionality without problems, but on the other hand you want to keep it small for the memory and yet fast for retrieving values. 625 more words

## Tags » Reinforcement Learning

#### Markov decision processes

Markov decision processes (MDPs), named after Andrey Markov, provide a mathematical framework for modeling decision making in situations where outcomes are partlyrandom and partly under the control of a decision maker. 463 more words