Runtime Monitors for Markov Decision Processes.
Sebastian JungesHazem TorfahSanjit A. SeshiaPublished in: CAV (2) (2021)
Keyphrases
- markov decision processes
- state space
- optimal policy
- finite state
- reinforcement learning
- transition matrices
- reachability analysis
- dynamic programming
- decision theoretic planning
- risk sensitive
- policy iteration
- planning under uncertainty
- state and action spaces
- finite horizon
- model based reinforcement learning
- average cost
- partially observable
- infinite horizon
- action space
- decision processes
- factored mdps
- reward function
- average reward
- markov decision process
- real time dynamic programming
- decision making
- probabilistic planning
- state abstraction
- least squares
- multi agent