Continuous-Time Stochastic Policy Iteration of Adaptive Dynamic Programming.
Qinglai WeiTianmin ZhouJingwei LuYu LiuShuai SuJun XiaoPublished in: IEEE Trans. Syst. Man Cybern. Syst. (2023)
Keyphrases
- policy iteration
- dynamic programming
- markov decision processes
- optimal control
- stochastic approximation
- optimal policy
- sample path
- policy iteration algorithm
- state space
- infinite horizon
- markov decision problems
- reinforcement learning
- approximate dynamic programming
- markov chain
- finite state
- markov decision process
- markov processes
- model free
- least squares
- linear programming
- average reward
- factored mdps
- monte carlo
- partially observable
- policy evaluation
- stochastic processes
- convergence rate
- asymptotic analysis
- temporal difference
- state dependent
- stereo matching
- action space
- long run
- fixed point
- linear program