HIGHLIGHTS
- who: Krishnendu Chatterjee and collaborators from the (UNIVERSITY) have published the Article: The Complexity of POMDPs with Long-run Average Objectives, in the Journal: (JOURNAL)
- what: The authors show that for every blind MDP with long-run average objectives, for every ε > 0, there is finite-recall strategy that achieves expected reward within ε of the optimal value. For POMDPs with parity objectives, even qualitative problems are Σ02 -complete, whereas the authors show that for POMDPs with long-run average objectives the approximation problem is R.E.-complete (or Σ01 -complete).
SUMMARY
A . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.