Two families of indexable partially observable restless bandits and Whittle index computation.
Nima AkbarzadehAditya MahajanPublished in: Perform. Evaluation (2024)
Keyphrases
- partially observable
- dynamical systems
- reinforcement learning
- state space
- infinite horizon
- markov decision processes
- decision problems
- optimal control
- partial observability
- partially observable environments
- markov decision problems
- partial observations
- fully observable
- belief state
- action models
- semi markov
- belief space
- partially observable domains
- stochastic systems