Keyphrases
- markov decision processes
- policy iteration
- factored mdps
- optimization problems
- reachability analysis
- finite state
- state space
- learning algorithm
- decision processes
- dynamic programming
- policy evaluation
- average reward
- infinite horizon
- stochastic shortest path
- transition matrices
- optimal policy
- planning under uncertainty
- monte carlo
- efficient optimization
- decision theoretic planning
- least squares
- computational complexity
- reinforcement learning