The ODE Method for Asymptotic Statistics in Stochastic Approximation and Reinforcement Learning

Vivek Borkar, Shuhang Chen, Adithya Devraj +2

The paper concerns the $d$-dimensional stochastic approximation recursion, $${\theta }_{n+1}={\theta }_n+{\alpha }_{n+1}f({\theta }_n,{\Phi }_{n+1})$$ where $\{{\Phi }_n\}$ is a stochastic process on a general st…