[FEATURE] support non-stationary rewards

[thetawom]

Is your feature request related to a problem? Please describe.
Currently, the rewards distribution of each arm is fixed, so the library can't simulate non-stationary (restless) bandit problems.

Describe the solution you'd like
When implementing a custom Arm, there should be an update() function that can be overridden to update the reward distribution's parameters. Then each step, the ArmSet should call update() for each arm to advance its reward distribution.