Speeding Up the Convergence of Value Iteration in Partially Observable Markov Decision Processes
Nevin Lianwen ZhangWeihong ZhangPublished in: CoRR (2011)
Keyphrases
- partially observable markov decision processes
- finite state
- dynamical systems
- reinforcement learning
- decision problems
- planning under uncertainty
- belief state
- markov decision processes
- optimal policy
- dynamic programming
- continuous state
- partially observable markov
- state space
- belief space
- planning problems
- partially observable stochastic games
- sequential decision making problems
- stochastic domains
- multi agent
- partially observable domains
- convergence rate
- average reward
- partially observable
- decision making
- stochastic shortest path
- knowledge base
- decision trees
- markov decision process
- initial state
- approximate solutions
- infinite horizon
- optimal control