Deciding the Value 1 Problem for $\sharp$ -acyclic Partially Observable Markov Decision Processes.
Hugo GimbertYoussouf OualhadjPublished in: SOFSEM (2014)
Keyphrases
- partially observable markov decision processes
- finite state
- dynamical systems
- reinforcement learning
- decision problems
- belief state
- dynamic programming
- np hard
- planning under uncertainty
- continuous state
- state space
- optimal policy
- belief space
- markov decision processes
- partially observable stochastic games
- partial observability
- approximate solutions
- planning problems
- partially observable markov
- partially observable domains
- multi agent
- stochastic domains
- sequential decision making problems
- partially observable markov decision process
- dec pomdps
- initial state
- partially observable