Optimal Continuous State POMDP Planning With Semantic Observations: A Variational Approach.
Luke BurksIan LoefgrenNisar R. AhmedPublished in: IEEE Trans. Robotics (2019)
Keyphrases
- continuous state
- planning problems
- partially observable markov decision processes
- state dependent
- reinforcement learning
- control policies
- dynamic programming
- robot navigation
- finite state
- domain independent
- dec pomdps
- policy search
- point based value iteration
- continuous state spaces
- optimal plans
- heuristic search
- optimal policy
- action space
- state space
- planning domains
- belief state
- dynamical systems
- domain specific
- continuous action
- optimal solution
- optimal control
- decision problems
- real valued
- belief space
- steady state
- infinite horizon
- queueing networks
- stochastic processes
- autonomous robots
- control policy
- probability distribution
- computational complexity