Questions tagged [dynamic-programming]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
0
votes
0answers
13 views

policy evaluation doesn't converge to an optimal policy, what does it converge to?

from suttons book, page 75 we get this notion of starting with a completely arbitrary policy and calculating value function for all s given that policy (i guess initializing all values at zero) ...
0
votes
0answers
8 views

GPU Parallelization: Kernel for Value Function Iteration on Matlab

(I crossposted on stackoverflow, I'm not sure where this question best fits.) I'd like to write a matlab function that does Value Function Iteration on GPU. What I have in mind is very similar to ...
1
vote
1answer
125 views

Dyna-Q Algorithm Reinforcement Learning

In step(f) of the Dyna-Q algorithm we plan by taking random samples from the experience/model for some steps. Wouldn't it be more efficient if we construct an MDP from experience by computing the ...
0
votes
0answers
12 views

Final conditions/end function in discrete choice dynamic programming (dynamic structural estimation)

Could anyone point me to a paper than employs an end function or final conditions in a dynamic structural estimation model? Many thanks
0
votes
1answer
70 views

Unique game problem (ML, DP, PP etc) [closed]

Looking for a solution to my below game problem. I believe it to be some sort of dynamic programming, machine learning, or probabilistic programming challenge, but am unsure... This is my original ...
0
votes
0answers
26 views

About the time differences in the Bellman equation

I am trying to grasp fundamental mathematics behind the Reinforcement Learning and so far I have unterstood how the Value Iteration and Policy algorithms do converge (contractions, etc.) I have still ...
2
votes
0answers
41 views

Understanding Approximate Dynamic Programming

I am trying to write a paper for my optimization class about Approximate Dynamic Programming. I found a few good papers but they all seem to dive straight into the material without talking about the ...
4
votes
1answer
660 views

Why are the value and policy iteration dynamic programming algorithms?

Algorithms like policy iteration and value iteration are often classified as dynamic programming methods that try to solve the Bellman optimality equations. My current understanding of dynamic ...