When Players Affect Target Values: Modeling and Solving Dynamic Partially Observable Security Games.
Xinrun WangMilind TambeBranislav BosanskýBo AnPublished in: GameSec (2019)
Keyphrases
- partially observable
- markov decision problems
- markov decision processes
- state space
- dynamical systems
- infinite horizon
- dynamic environments
- decision problems
- action models
- reinforcement learning
- partial observability
- belief state
- partial observations
- partially observable environments
- reward function
- optimal control
- hidden markov models
- search algorithm