Bias-policy iteration based adaptive dynamic programming for unknown continuous-time linear systems.
Huaiyuan JiangBin ZhouPublished in: Autom. (2022)
Keyphrases
- linear systems
- policy iteration
- dynamic programming
- markov decision processes
- optimal control
- dynamical systems
- optimal policy
- state space
- infinite horizon
- markov decision problems
- reinforcement learning
- sufficient conditions
- fixed point
- sample path
- markov decision process
- finite state
- model free
- markov chain
- sparse linear systems
- linear programming
- average reward
- coefficient matrix
- least squares
- temporal difference
- partially observable markov decision processes
- long run
- average cost
- graphical models
- genetic algorithm
- neural network