Skip to main content
MathOverflow
SBF's user avatar
SBF's user avatar
SBF's user avatar
SBF
  • Member for 13 years, 11 months
  • Last seen more than a month ago
  • Berlin
Profile Activity

373 Actions

All Accepts Posts Badges Comments Revisions Reviews Suggestions
answered
Is there an easy way to convert a non-deterministic optimal policy to a deterministic optimal policy for a given MDP?
revised
Conditions for existence of dominating $\sigma$-finite measure for all conditional distributions
made the title more clear
comment
Is there an easy way to convert a non-deterministic optimal policy to a deterministic optimal policy for a given MDP?
Can't you just follow a greedy policy in this case? AFAIK, optimal non-deterministic policy is any probability measure on maximal set of the value function, so picking just any point there would suffice.
comment
Infinitesimal generator and stationarity
What exactly does your "moreover" statement mean?
comment
Conditions for existence of dominating $\sigma$-finite measure for all conditional distributions
One sufficient condition (even though trivial, perhaps) is that if $P \in Q$ and $P' \ll P$ then $P' \in Q$
suggested
Approve
Conditions for existence of dominating $\sigma$-finite measure for all conditional distributions
answered
Measurable $\epsilon$-optimal selection with an analytically measurable stochastic kernel
comment
Generalizations of the Birkhoff-von Neumann Theorem
Can you provide a reference to the last sentence? Namely, what are the extreme points here. Related to this question
comment
Extreme couplings
@michael: afaik in the discrete case there is going to be a finite number of extreme points, however no, I don't know how to describe them nicely.
asked
Extreme couplings
accepted
Convex hulls of families of probability measures
comment
Bounds on Wasserstein (Kantorovich) distance
@FedorPetrov: a typo, $\lambda = \gamma$
revised
Bounds on Wasserstein (Kantorovich) distance
deleted 2 characters in body
comment
Bounds on Wasserstein (Kantorovich) distance
@NateEldredge: added. True for the $\nu$, and $P$ is the joint distribution with the left marginal $\mu$ and conditional probability $P$.
revised
Bounds on Wasserstein (Kantorovich) distance
added 287 characters in body
asked
Bounds on Wasserstein (Kantorovich) distance
revised
Stochastic equation
added 594 characters in body
asked
Stochastic equation
comment
Euler-like identity for partition function
Would it be of any help that $f(x)f(-x) = f(x^2)$?
awarded
 Popular Question
1 2
3
4 5
…
19