Epsilon Greedy Policy
[numeric(1) in [0, 1]] Ratio of random exploration in epsilon-greedy action selection.
numeric(1) in [0, 1]
makePolicy("epsilon.greedy", epsilon = 0.1) makePolicy("greedy")
makePolicy("epsilon.greedy", epsilon = 0.1)
makePolicy("greedy")
policy = makePolicy("epsilon.greedy", epsilon = 0.1)