Hierarchical algorithms for discounted and weighted Markov decision processes.
Mohammed AbbadCherki DaouiPublished in: Math. Methods Oper. Res. (2003)
Keyphrases
- markov decision processes
- policy iteration
- optimal policy
- factored mdps
- reachability analysis
- dynamic programming
- state space
- finite horizon
- learning algorithm
- finite state
- infinite horizon
- planning under uncertainty
- average reward
- average cost
- partially observable
- reinforcement learning
- transition matrices
- decision processes
- decision problems
- decision theoretic planning
- computational complexity
- stochastic shortest path
- semi markov decision processes
- state and action spaces
- policy evaluation
- partially observable markov decision processes
- multi agent