Indexability and Rollout Policy for Multi-State Partially Observable Restless Bandits.
Rahul MeshramKesav KazaPublished in: CDC (2021)
Keyphrases
- partially observable
- state space
- decision problems
- dynamical systems
- infinite horizon
- reinforcement learning
- markov decision processes
- markov decision problems
- partially observable environments
- partial observations
- belief state
- fully observable
- partial observability
- hidden state
- optimal control
- reward function
- optimal policy
- action models
- partially observable domains
- partially observable markov decision processes
- orders of magnitude
- stochastic systems
- dynamic programming
- markov decision process
- decision making
- multi agent
- state variables
- np hard
- conditional random fields
- markov chain