Skip to main content
MathOverflow

Return to Question

added 103 characters in body
Source Link
user812951
user812951
  • 154
  • 5

I have a question that is an extension of this one. My question is: Can we say that for every policy, there exists a deterministic policy in case of constraineda finite-state, finite-action infinite-horizon discounted (where the discount factor is fixed)constrained MDP, where the costs and transition probabilities are known? (i.e. when there are multiple discounted costs with one cost in the objective and the rest with bounds in the constraints)

I have a question that is an extension of this one. My question is: Can we say that for every policy, there exists a deterministic policy in case of constrained discounted MDP? (i.e. when there are multiple discounted costs with one cost in the objective and the rest with bounds in the constraints)

I have a question that is an extension of this one. My question is: Can we say that for every policy, there exists a deterministic policy in case of a finite-state, finite-action infinite-horizon discounted (where the discount factor is fixed)constrained MDP, where the costs and transition probabilities are known? (i.e. when there are multiple discounted costs with one cost in the objective and the rest with bounds in the constraints)

formatted link, fixed "doubt"
Source Link
YCor
YCor
  • 63.9k
  • 5
  • 187
  • 286

constrained Constrained MDP

I have a doubtquestion that is an extension of this question: https://mathoverflow.net/questions/44677/is-there-mdps-markow-decision-process-which-have-a-non-deterministic-optimal-p#:~:text=4%20Answers&text=If%20there%20is%20an%20optimal,is%20a%20deterministic%20optimal%20policy.&text=So%20all%20actions%20will%20give,improve%20on%20all%20Markovian%20strategies.
this one. My question is: Can we say that for every policy, there exists a deterministic policy in case of constrained discounted MDP?  (i.e. when there are multiple discounted costs with one cost in the objective and the rest with bounds in the constraints)

constrained MDP

I have a doubt that is an extension of this question: https://mathoverflow.net/questions/44677/is-there-mdps-markow-decision-process-which-have-a-non-deterministic-optimal-p#:~:text=4%20Answers&text=If%20there%20is%20an%20optimal,is%20a%20deterministic%20optimal%20policy.&text=So%20all%20actions%20will%20give,improve%20on%20all%20Markovian%20strategies.
My question is: Can we say that for every policy, there exists a deterministic policy in case of constrained discounted MDP?(i.e. when there are multiple discounted costs with one cost in the objective and the rest with bounds in the constraints)

Constrained MDP

I have a question that is an extension of this one. My question is: Can we say that for every policy, there exists a deterministic policy in case of constrained discounted MDP?  (i.e. when there are multiple discounted costs with one cost in the objective and the rest with bounds in the constraints)

Source Link
user812951
user812951
  • 154
  • 5

constrained MDP

I have a doubt that is an extension of this question: https://mathoverflow.net/questions/44677/is-there-mdps-markow-decision-process-which-have-a-non-deterministic-optimal-p#:~:text=4%20Answers&text=If%20there%20is%20an%20optimal,is%20a%20deterministic%20optimal%20policy.&text=So%20all%20actions%20will%20give,improve%20on%20all%20Markovian%20strategies.
My question is: Can we say that for every policy, there exists a deterministic policy in case of constrained discounted MDP?(i.e. when there are multiple discounted costs with one cost in the objective and the rest with bounds in the constraints)