The Complexity of POMDPs with Long-run Average Objectives.
Krishnendu ChatterjeeRaimundo SaonaBruno ZiliottoPublished in: CoRR (2019)
Keyphrases
- long run
- average cost
- short run
- optimal policy
- average reward
- infinite horizon
- markov decision processes
- decision problems
- expected cost
- reinforcement learning
- heavy traffic
- dynamic programming
- queueing networks
- control policy
- computational complexity
- finite state
- partially observable markov decision processes
- machine learning
- exchange rate
- partially observable
- state space
- long term
- markov decision process