Keyphrases
- markov decision problems
- linear programming
- reinforcement learning
- state space
- partially observable
- special case
- np hard
- optimal policy
- decision theoretic
- decision processes
- dynamic programming
- transition probabilities
- utility function
- markov decision processes
- computational complexity
- expected utility
- queueing networks
- average cost
- action space
- linear program
- decision problems
- orders of magnitude
- supervised learning
- neural network
- state transitions
- policy iteration
- reward function
- infinite horizon
- long run
- finite state
- real valued
- monte carlo
- markov chain