A Generalized Reduced Linear Program for Markov Decision Processes.
Chandrashekar LakshminarayananShalabh BhatnagarPublished in: CoRR (2014)
Keyphrases
- markov decision processes
- linear program
- dynamic programming
- linear programming
- average cost
- semi infinite
- approximate dynamic programming
- optimal policy
- state space
- factored mdps
- finite state
- policy iteration
- stationary policies
- optimal solution
- column generation
- reinforcement learning
- objective function
- transition matrices
- partially observable
- infinite horizon
- action sets
- model based reinforcement learning
- markov decision process
- planning under uncertainty
- stochastic programming
- finite horizon
- decision theoretic planning
- reward function
- action space
- decision processes
- reachability analysis
- average reward
- optimal control
- np hard
- multistage
- real time dynamic programming