Planning for multiple measurement channels in a continuous-state POMDP.
Mikko LauriRisto RitalaPublished in: Ann. Math. Artif. Intell. (2013)
Keyphrases
- continuous state
- planning problems
- partially observable markov decision processes
- finite state
- reinforcement learning
- robot navigation
- dec pomdps
- policy search
- heuristic search
- state dependent
- belief state
- point based value iteration
- decision problems
- control policies
- state space
- markov decision processes
- action space
- dynamic programming
- state variables
- dynamical systems
- domain independent
- continuous state spaces
- optimal policy
- continuous action
- planning domains
- belief space