MDPFuzz: testing models solving Markov decision processes.
Qi PangYuanyuan YuanShuai WangPublished in: ISSTA (2022)
Keyphrases
- markov decision processes
- transition matrices
- semi markov decision processes
- state space
- reinforcement learning
- optimal policy
- partially observable
- finite state
- reachability analysis
- dynamic programming
- probabilistic model
- finite horizon
- average cost
- risk sensitive
- markov decision problems
- average reward
- decision processes
- action space
- decision problems
- machine learning
- reinforcement learning algorithms
- decision theoretic planning
- reward function
- model based reinforcement learning
- dynamical systems
- stochastic shortest path