Reinforcement Learning: Theory and Algorithms

← Back to document page

•An action space A, which also may be discrete or infinite. For mathematical convenience, we will assume that Ais finite. •A transition function P: SA! ( S), where ( S) is the space of probability distributions over S(i.e., the probability simplex). P(s0js;a) is the probability of transitioning into state s0upon taking action ain state s ...

  Learning, Theory, Discrete, Algorithm, Reinforcement, Reinforcement learning, Theory and algorithms