On constrained optimization of the Klimov network and related Markov decision processes.
Armand M. MakowskiAdam ShwartzPublished in: IEEE Trans. Autom. Control. (1993)
Keyphrases
- markov decision processes
- constrained optimization
- state space
- optimal policy
- constrained optimization problems
- finite state
- transition matrices
- dynamic programming
- average reward
- reinforcement learning
- planning under uncertainty
- unconstrained optimization
- reinforcement learning algorithms
- markov decision process
- penalty function
- objective function
- reachability analysis
- policy iteration
- factored mdps
- action space
- model based reinforcement learning
- infinite horizon
- decision theoretic planning
- machine learning
- action sets
- lagrange multipliers
- finite horizon
- partially observable
- multi agent
- cost function
- average cost
- least squares
- linear programming
- decision problems