Constrained Optimization for Average Cost Continuous-Time Markov Decision Processes.
Xianping GuoPublished in: IEEE Trans. Autom. Control. (2007)
Keyphrases
- constrained optimization
- average cost
- markov decision processes
- state space
- stationary policies
- optimal control
- finite state
- optimal policy
- markov chain
- approximate dynamic programming
- reinforcement learning
- infinite horizon
- objective function
- dynamic programming
- finite horizon
- transition matrices
- decision theoretic planning
- policy iteration
- dynamical systems
- initial state
- risk sensitive
- markov decision process
- action space
- partially observable
- control policy
- multistage
- action sets
- stochastic processes
- long run
- linear programming
- reward function
- decision making
- semi parametric
- search space
- sufficient conditions
- linear program