Scheduling sensors for monitoring sentient spaces using an approximate POMDP policy.
Ronen VaisenbergAlessio Della MottaSharad MehrotraDeva RamananPublished in: PerCom (2013)
Keyphrases
- policy evaluation
- point based value iteration
- optimal policy
- model free reinforcement learning
- partially observable markov decision processes
- least squares
- real time
- partially observable
- markov decision process
- reinforcement learning
- partially observable markov decision process
- markov decision processes
- temporal difference
- monitoring system
- everyday life
- policy iteration
- model free
- scheduling problem
- health monitoring
- sensor networks
- nearest neighbor searching
- data acquisition
- sensing devices
- scheduling algorithm
- finite state
- state space
- infinite horizon
- wireless sensor
- round robin
- markov decision problems
- belief state
- function approximation
- continuous state
- sensor data
- scheduling policies
- state and action spaces
- dynamic programming
- selective perception
- state dependent
- decision theoretic
- reward function
- admission control
- planning problems
- long run
- multi sensor
- approximate solutions
- resource allocation
- belief space
- control policies
- daily life
- policy gradient
- hidden state
- decision problems
- wearable sensors
- policy search
- human operators
- parallel machines