Simulation-Based Optimization Algorithms for Finite-Horizon Markov Decision Processes.
Shalabh BhatnagarMohammed Shahid AbdullaPublished in: Simul. (2008)
Keyphrases
- markov decision processes
- finite horizon
- optimal policy
- policy iteration
- infinite horizon
- factored mdps
- optimal stopping
- finite state
- markov decision process
- reachability analysis
- dynamic programming
- state space
- reinforcement learning
- average cost
- control policies
- decision theoretic planning
- average reward
- transition matrices
- learning algorithm
- partially observable markov decision processes
- action space
- partially observable
- multistage
- search algorithm
- upper and lower bounds
- long run
- computational complexity
- expected reward
- machine learning
- stochastic shortest path