4

A non-starving policy is a (behavior) policy that is theoretically guaranteed to visit each state and take all possible actions from each state an infinite number of times, so that to always update $Q(s, a)$, $\forall s, \forall a$, an infinite number of times. In the context of off-policy prediction, this criterion implies that any trajectory will have no ...


3

The concepts of on-policy vs off-policy and online vs offline are separate, but do interact to make certain combinations more feasible. When looking at this, it is worth also considering the difference between prediction and control in Reinforcement Learning (RL). Online vs Offline These concepts are not specific to RL, many learning systems can be ...


3

Absolutely, it’s a really interesting problem. Here is a paper detailing off policy actor critic. This is important because this method can also support continuous actions. The general idea of off-policy algorithms is to compare the actions performed by a behaviour policy (which is actually acting in the world) with the actions the target policy (the ...


2

The twist here is that the $a_{t+1}$ in (11) and the $\mu(s_{t+1})$ in (16) are the same and actually the $a_t$ in the on-policy case and the $a_t$ in the off-policy case are different. The key to the understanding is that in on-policy algorithms you have to use actions (and generally speaking trajectories) generated by the policy in the updating steps (to ...


1

If your game agent performs any kind of advance learning from self play or database of moves, that will generate parameters for some kind of model (e.g. a table of expected values, or neural network weights to select a preferred action). This is unavoidable, and if you want to re-use the results of that machine learning, you absolutely have to store the ...


1

Multiplying the entire update by $\rho$ has the desirable property that experience affects $Q$ less when the behavior policy is unrelated to the target policy. In the extreme, if the trajectory taken has zero probability under the target policy, then $Q$ isn't updated at all, which is good. Alternatively, if only $G$ is scaled by $\rho$, taking zero ...


1

I don't think the section was written in haste. I think they just didn't have space to include the whole proof. It's a bit involved, so they just gave concepts. An Emphatic Approach to the Problem of Off-policy Temporal-Difference Learning gives a proof of stability. At least parts of it should seem familiar if you've read Sutton and Barto's proof of the ...


1

It's because, in the actor-critic algorithm, the objective function is an expectation under the $\tau$ of the policy. If we want to use off-policy data, we have to resort to importance sampling relative to the other policy.


Only top voted, non community-wiki answers of a minimum length are eligible