CS234 (CS234)

CS 234 ASSIGNMENT 2 2021/2022.0 Distributions induced by a policy (13 pts) In this problem, we’ll work with an infinite-horizon MDP M = hS, A, R, T , γi and consider stochastic policies of the form π : S → ∆(A) 1 . Additionally, we’ll assume that M has a single, fixed starting state s 0 ∈ S for simplicity. (a) (written, 3 pts) Consider a fixed stochastic policy and imagine running several rollouts of this policy within the environment. Naturally, depending on the stochastici...

CS 234 ASSIGNMENT 2 2021/2022 – Stanford University. Distributions induced by a policy (13 pts) In this problem, we’ll work with an infinite-horizon MDP M = hS, A, R, T , γi and consider stochastic policies of the form π : S → ∆(A) 1 . Additionally, we’ll assume that M has a single, fixed starting state s 0 ∈ S for simplicity. (a) (written, 3 pts) Consider a fixed stochastic policy and imagine running several rollouts of this policy within the environment. Naturally, depe...