Verification of Markov Decision Processes Using Learning Algorithms.
Tomás BrázdilKrishnendu ChatterjeeMartin ChmelikVojtech ForejtJan KretínskýMarta Z. KwiatkowskaDavid ParkerMateusz UjmaPublished in: ATVA (2014)
Keyphrases
- markov decision processes
- learning algorithm
- reinforcement learning
- reinforcement learning algorithms
- finite state
- state space
- transition matrices
- dynamic programming
- reachability analysis
- policy iteration
- finite horizon
- decision theoretic planning
- machine learning
- optimal policy
- machine learning algorithms
- model checking
- partially observable
- average cost
- action sets
- infinite horizon
- supervised learning
- average reward
- learning problems
- learning agent
- action space
- decision processes
- planning under uncertainty
- risk sensitive
- markov decision process
- model based reinforcement learning
- reward function
- markov decision problems
- policy evaluation
- factored mdps
- function approximation
- transfer learning