Quasi-Deterministic Partially Observable Markov Decision Processes.
Camille BesseBrahim Chaib-draaPublished in: ICONIP (1) (2009)
Keyphrases
- partially observable markov decision processes
- fully observable
- stochastic domains
- finite state
- reinforcement learning
- partially observable domains
- planning under uncertainty
- dynamical systems
- belief space
- optimal policy
- dynamic programming
- partial observability
- belief state
- decision problems
- planning problems
- state space
- partially observable stochastic games
- continuous state
- multi agent
- hidden state
- markov decision processes
- point based value iteration
- partially observable markov
- sequential decision making problems
- approximate solutions
- partially observable
- dynamic environments
- markov chain
- orders of magnitude
- dec pomdps
- markov decision problems
- partially observable markov decision process
- linear programming
- mobile robot
- search algorithm
- knowledge base
- decision making