Positivity-hardness results on Markov decision processes.
Jakob PiribauerChristel BaierPublished in: CoRR (2023)
Keyphrases
- markov decision processes
- state space
- optimal policy
- finite state
- dynamic programming
- reinforcement learning
- transition matrices
- reinforcement learning algorithms
- factored mdps
- average reward
- reachability analysis
- model based reinforcement learning
- decision theoretic planning
- decision processes
- finite horizon
- policy iteration
- partially observable
- np hard
- computational complexity
- planning under uncertainty
- markov decision process
- action space
- state and action spaces
- average cost
- infinite horizon
- real valued
- interval estimation