Error Bounds of Adaptive Dynamic Programming Algorithms for Solving Undiscounted Optimal Control Problems.
Derong LiuHongliang LiDing WangPublished in: IEEE Trans. Neural Networks Learn. Syst. (2015)
Keyphrases
- error bounds
- dynamic programming algorithms
- markov decision problems
- optimal control problems
- dynamic programming
- optimal control
- optimal policy
- theoretical analysis
- linear programming
- partially observable
- worst case
- state space
- np complete problems
- markov decision processes
- infinite horizon
- decision theoretic
- reinforcement learning
- policy iteration
- solving nonlinear
- decision processes
- queueing networks
- constraint satisfaction
- utility function