Function Rl-Episode
(
rl-episode )
Do one episode until a termination observation occurs or until steps have
elapsed, whichever comes first. As you might imagine, this is done by
calling rl-start, then rl-step until the terminal observation occurs. If
max-num-steps is set to 0, it is taken to be the case where there is no
limitation on the number of steps taken and rl-episode will continue until
a termination observation occurs. If no terminal observation is reached
before max-num-steps is reached, the agent does not call agent-end, it
simply stops.
PARAMETERS:
exp : experiment in use [experiment]
max-num-steps : maximum number of steps [0 < integer]
[optional parameter, default is no limit]
RETURNS:
terminal flag after the step [boolean]