Solving Partially Observable Markov Decision Processes by Neural Networks.
S. A. Velázquez LermaRené AlquézarPublished in: IIA/SOCO (1999)
Keyphrases
- partially observable markov decision processes
- neural network
- sequential decision making problems
- finite state
- reinforcement learning
- dynamical systems
- decision theoretic planning
- belief state
- planning under uncertainty
- partial observability
- continuous state
- belief space
- optimal policy
- markov decision problems
- decision problems
- stochastic domains
- partially observable
- partially observable stochastic games
- markov decision processes
- dynamic programming
- state space
- dec pomdps
- partially observable markov
- planning problems
- dynamic environments
- markov chain
- partially observable domains
- point based value iteration
- computational complexity
- multi agent