Keyphrases
- state variables
- bandit problems
- state space
- decision problems
- partially observable markov decision processes
- belief state
- partially observable
- reinforcement learning
- multi armed bandits
- optimal policy
- dynamic systems
- markov decision processes
- expected utility
- influence diagrams
- markov decision problems
- dynamical systems
- random variables
- dynamic bayesian networks
- dynamic programming
- finite state
- heuristic search
- particle filter
- utility function
- reward function
- markov chain
- search space
- partial least square regression
- multi armed bandit problems
- neural network
- theoretical framework
- computational complexity
- search algorithm
- multi agent
- artificial intelligence