Learning Algorithms for Verification of Markov Decision Processes.
Tomás BrázdilKrishnendu ChatterjeeMartin ChmelikVojtech ForejtJan KretínskýMarta KwiatkowskaTobias MeggendorferDavid ParkerMateusz UjmaPublished in: CoRR (2024)
Keyphrases
- markov decision processes
- learning algorithm
- reinforcement learning algorithms
- reinforcement learning
- state space
- optimal policy
- finite state
- policy iteration
- finite horizon
- factored mdps
- dynamic programming
- transition matrices
- markov decision process
- learning problems
- partially observable
- machine learning
- model based reinforcement learning
- model checking
- reachability analysis
- policy evaluation
- decision theoretic planning
- learning tasks
- infinite horizon
- action space
- state and action spaces
- planning under uncertainty
- average reward
- decision processes
- supervised learning
- machine learning algorithms
- risk sensitive
- average cost
- learning rate
- function approximation
- data mining
- state abstraction
- action selection
- real valued