Off-Policy Risk Assessment for Markov Decision Processes.
Audrey HuangLiu LeqiZachary C. LiptonKamyar AzizzadenesheliPublished in: AISTATS (2022)
Keyphrases
- risk assessment
- markov decision processes
- risk management
- finite state
- state space
- network security
- decision making
- optimal policy
- transition matrices
- dynamic programming
- reinforcement learning
- decision theoretic planning
- information security
- planning under uncertainty
- average cost
- policy iteration
- partially observable
- model based reinforcement learning
- average reward
- decision support system
- reachability analysis
- state and action spaces
- markov decision process
- action space
- reward function
- infinite horizon
- machine learning
- power plant
- action sets
- real time dynamic programming
- artificial neural networks
- evolutionary algorithm
- software engineering