Generalization from Examples
- Often there are way too many states to build a
table,
- or the state is not completely visible.
- We can fix this by replacing with a neural net
or other generalizer.
- For example, encode as the
network inputs and train it to output the target
values of given by the training rules.
- Or, train a separate network for each action, using
the state as input and as output.
- Or, train one network with the state as input but
with one output for each action.
- TD-Gammon used neural nets and Backpropagation.
José M. Vidal
.
22 of 22