On Skolem-hardness and saturation points in Markov decision processes.
Jakob PiribauerChristel BaierPublished in: CoRR (2020)
Keyphrases
- markov decision processes
- state space
- finite state
- reinforcement learning
- optimal policy
- dynamic programming
- transition matrices
- policy iteration
- planning under uncertainty
- decision theoretic planning
- reinforcement learning algorithms
- reachability analysis
- average cost
- factored mdps
- markov decision process
- finite horizon
- average reward
- model based reinforcement learning
- action space
- partially observable
- action sets
- infinite horizon
- first order logic
- np hard
- decision makers
- risk sensitive
- decision processes
- decision diagrams
- semi markov decision processes
- computational complexity