New answers tagged

1 vote

What happens when the probability of either one of the policies is 0 in Importance Sampling?

Very simply, one of the requirements of off-policy RL to converge, is that the behavioral policy $b$ has at least the same support of the target policy $\pi$, thus: $$ \forall s \in S \forall a \in A \...
Alberto's user avatar
  • 1,358
2 votes

What happens when the probability of either one of the policies is 0 in Importance Sampling?

Background: Importance sampling is used in many off-policy RL algorithms when the data is generated with one policy, yet it is being used to update another policy. The policy generating the data is ...
DeepQZero's user avatar
  • 1,332

Top 50 recent answers are included