Modified λ-Policy Iteration Based Adaptive Dynamic Programming for Unknown Discrete-Time Linear Systems.
Huaiyuan JiangBin ZhouGuang-Ren DuanPublished in: IEEE Trans. Neural Networks Learn. Syst. (2024)
Keyphrases
- linear systems
- policy iteration
- markov decision processes
- dynamic programming
- optimal policy
- finite state
- sufficient conditions
- infinite horizon
- reinforcement learning
- markov decision problems
- dynamical systems
- fixed point
- model free
- coefficient matrix
- sample path
- linear programming
- state space
- optimal control
- least squares
- markov decision process
- average reward
- sparse linear systems
- average cost
- temporal difference
- linear program
- markov random field
- multi objective