....
As per convention, tex2html_wrap_inline258 represents the target (optimal) function. 
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
....
Although we think of tex2html_wrap_inline486 and tex2html_wrap_inline488 as functions from angles to probabilities, we will use -1 rather than 0 as the lower bound of the range. This representation simplifies many of our illustrative calculations. 
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
...locations.
For particularly large values of M it is useful to generalize training examples to more memory locations, particularly at the early stages of learning. However for the values of M considered in this paper, we always generalize to the 2 nearest memory locations. 
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
...zero,
Recall that a memory value of 0 is equivalent to a probability of .5, representing no reason to believe that the action will succeed or fail. 
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
...50,
In the simulator, ``50'' represents 50 cm/s. We omit the units in the remainder of the paper. 
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.

Peter Stone
Mon Dec 11 15:42:40 EST 1995