Bounded-Parameter Partially Observable Markov Decision Processes.
Yaodong NiZhi-Qiang LiuPublished in: ICAPS (2008)
Keyphrases
- partially observable markov decision processes
- finite state
- planning under uncertainty
- reinforcement learning
- dynamical systems
- decision problems
- belief state
- continuous state
- dynamic programming
- partially observable stochastic games
- belief space
- optimal policy
- markov decision processes
- partially observable domains
- fully observable
- state space
- planning problems
- stochastic domains
- sequential decision making problems
- partially observable markov
- multi agent
- partial observability
- predictive state representations
- infinite horizon
- point based value iteration
- partially observable markov decision process
- approximate solutions
- partially observable
- column generation
- np hard
- search algorithm