Total Reward Variance in Discrete and Continuous Time Markov Chains.
Karel SladkýNico M. van DijkPublished in: OR (2004)
Keyphrases
- continuous time markov chains
- markov processes
- total reward
- poisson distribution
- markov process
- markov chain
- stochastic processes
- markov decision processes
- reinforcement learning
- random fields
- reinforcement learning algorithms
- optimal policy
- action selection
- numerically stable
- average reward
- non stationary
- machine learning
- stochastic process