Block-scaling of value-iteration for discounted Markov renewal programming.
Paul J. SchweitzerPublished in: Ann. Oper. Res. (1991)
Keyphrases
- markov decision processes
- markov chain
- infinite horizon
- average reward
- state space
- dynamic programming
- optimal policy
- finite state
- markov decision process
- finite horizon
- programming language
- computer programming
- long run
- heuristic search
- markov processes
- partially observable
- average cost
- programming environment
- reinforcement learning
- development environment
- optimal control
- policy iteration
- markov process
- steady state
- machine learning
- semi markov
- image blocks
- markov model
- confidence intervals
- directed acyclic graph
- block wise