Partial-Information State-Based Optimization of Partially Observable Markov Decision Processes and the Separation Principle.
Xi-Ren CaoDe-Xin WangLi QiuPublished in: IEEE Trans. Autom. Control. (2014)
Keyphrases
- partial information
- partially observable markov decision processes
- partial observability
- belief state
- fully observable
- state space
- reinforcement learning
- incomplete information
- dynamical systems
- planning under uncertainty
- planning problems
- domain independent
- dynamic environments
- dynamic programming
- state variables
- partially observable
- sensing actions
- predictive state representations
- partially observable domains
- infinite horizon
- decision problems
- markov decision processes
- optimal policy
- markov chain
- knowledge representation
- computational complexity
- objective function