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, $$\hat{I}{¸}_{n+1}=\hat{I}{¸}_n+\hat{I}{\pm }_{n+1}f(\hat{I}{¸}_n,\hat{I}{¦}_{n+1})$$ where $\{\hat{I}{¦}_n\}$ is a stochastic process on a gene…