Keyphrases
- markov decision processes
- transition matrices
- infinite horizon
- policy iteration
- neural network
- policy evaluation
- optimal policy
- finite horizon
- markov decision process
- finite state
- state space
- average reward
- artificial neural networks
- markov decision problems
- average cost
- reinforcement learning
- partially observable
- radial basis function
- dynamic programming
- discounted reward
- planning under uncertainty
- decision making
- decision processes
- action space
- long run
- inventory level
- reinforcement learning algorithms
- decision problems
- multistage
- policy iteration algorithm