The n th-Order Bias Optimality for Multichain Markov Decision Processes.
Xi-Ren CaoJunyu ZhangPublished in: IEEE Trans. Autom. Control. (2008)
Keyphrases
- markov decision processes
- average reward
- optimal policy
- finite state
- state space
- average cost
- dynamic programming
- transition matrices
- reachability analysis
- policy iteration
- planning under uncertainty
- decision theoretic planning
- reinforcement learning algorithms
- long run
- factored mdps
- semi markov decision processes
- reinforcement learning
- infinite horizon
- action sets
- finite horizon
- decision processes
- probabilistic planning
- decision diagrams
- model based reinforcement learning