Markov Reward Models and Markov Decision Processes in Discrete and Continuous Time: Performance Evaluation and Optimization.
Alexander GoubermanMarkus SieglePublished in: ROCKS (2012)
Keyphrases
- markov decision processes
- transition matrices
- reinforcement learning
- state space
- average reward
- markov chain
- finite state
- optimal policy
- policy iteration
- reward function
- markov processes
- dynamic programming
- planning under uncertainty
- discounted reward
- decision theoretic planning
- infinite horizon
- reinforcement learning algorithms
- expected reward
- learning algorithm
- stochastic processes
- stationary policies
- action sets
- total reward
- semi markov decision processes