A special case of partially observable Markov decision processes problem by event-based optimization.
Junyu ZhangPublished in: ICIT (2016)
Keyphrases
- special case
- partially observable markov decision processes
- belief space
- planning under uncertainty
- belief state
- finite state
- reinforcement learning
- dynamical systems
- computational complexity
- np hard
- dynamic programming
- partially observable markov
- stochastic domains
- continuous state
- markov decision processes
- state space
- search algorithm
- orders of magnitude
- decision theoretic planning
- multi agent
- partially observable domains
- learning algorithm