Keyphrases
- markov decision processes
- infinite horizon
- transition matrices
- markov decision process
- finite horizon
- optimal policy
- average cost
- dynamic programming
- discount factor
- policy iteration
- state space
- long run
- average reward
- reinforcement learning
- optimal control
- finite state
- total reward
- probabilistic model
- reinforcement learning algorithms
- partially observable
- mathematical model
- decision processes
- belief functions
- decision problems
- probability distribution
- stationary policies
- bayesian networks
- discounted reward
- search space
- markov decision problems
- planning under uncertainty
- reward function
- model free
- finite number
- optimal solution